Metadata
Title
Description
Graph Axes
Note: embed and flat are special keywords. embed spreads the points based on similarities in the text embedding. flat, as the name suggests, prevents distribution along an axis. These only take effect when both start and end values of an axis are set to the same special keyword.
X Axis
Y Axis
Z Axis
Prompts
Outputs generated: 40 / 40
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Positive
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Positive
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Positive
Output: Positive
Output: Negative
Output: Neutral
Output: Positive
Output: Negative
Output: Negative
Output: Neutral
Classify positive sentiment in various personal experiences.Positive sentiment classification results.Classify negative sentiment in various personal experiences.Negative sentiment classification results.Classify neutral sentiment in various personal experiences.Neutral sentiment classification results.
Showing 80 data points from 1 dataset: Sentiment Classification (Zero-shot)
Dataset
Type
Content
X
Y
Z
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I love spending time with my family. Sentiment:1.000.420.07
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.980.91
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The food at the restaurant was terrible. Sentiment:-1.000.33-0.00
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.57-0.41
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The movie was pretty average. Sentiment:0.000.350.03
Sentiment Classification (Zero-shot)
Output
Neutral0.000.99-0.97
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I had a fantastic day at the beach. Sentiment:1.000.330.02
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.970.91
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The service was really bad. Sentiment:-1.000.380.08
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.66-0.43
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The weather today is fine. Sentiment:0.000.43-0.07
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.980.91
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am extremely happy with my new job. Sentiment:1.000.440.01
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.950.91
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The meeting was a waste of time. Sentiment:-1.000.440.02
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.59-0.39
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The presentation was okay. Sentiment:0.000.440.04
Sentiment Classification (Zero-shot)
Output
Neutral0.000.95-0.95
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I enjoyed the concert last night. Sentiment:1.000.450.04
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.920.94
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I hate waking up early. Sentiment:-1.000.42-0.00
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.58-0.40
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The project is going well. Sentiment:1.000.390.07
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.940.92
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: My vacation was wonderful. Sentiment:1.000.39-0.02
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.920.95
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am disappointed with the product. Sentiment:-1.000.39-0.06
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.56-0.37
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The event was neither good nor bad. Sentiment:0.000.370.10
Sentiment Classification (Zero-shot)
Output
Neutral0.000.96-0.97
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The trip was amazing. Sentiment:1.000.440.09
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.950.93
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am not satisfied with the service. Sentiment:-1.000.380.11
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.67-0.42
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The movie was fine. Sentiment:0.000.350.13
Sentiment Classification (Zero-shot)
Output
Neutral0.000.95-0.96
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am thrilled with the results. Sentiment:1.000.480.05
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.951.00
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The food was disappointing. Sentiment:-1.000.440.10
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.65-0.43
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The weather is neither here nor there. Sentiment:0.000.400.03
Sentiment Classification (Zero-shot)
Output
Neutral0.000.96-0.99
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am overjoyed with my promotion. Sentiment:1.000.480.01
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.941.00
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The service at the cafe was poor. Sentiment:-1.000.360.08
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.65-0.43
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The book was okay. Sentiment:0.000.33-0.03
Sentiment Classification (Zero-shot)
Output
Neutral0.000.95-0.95
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I had a great time at the party. Sentiment:1.000.330.09
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.940.99
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am unhappy with my purchase. Sentiment:-1.000.460.02
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.55-0.38
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The movie was just average. Sentiment:0.000.390.02
Sentiment Classification (Zero-shot)
Output
Neutral0.001.00-0.99
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The experience was delightful. Sentiment:1.000.41-0.04
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.930.97
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I regret buying this item. Sentiment:-1.000.400.10
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.61-0.41
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The performance was so-so. Sentiment:0.000.46-0.05
Sentiment Classification (Zero-shot)
Output
Neutral0.000.99-1.00
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am excited about the new opportunities. Sentiment:1.000.360.04
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.910.94
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The customer service was awful. Sentiment:-1.000.470.07
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.61-0.42
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The weather is quite nice today. Sentiment:0.000.43-0.04
Sentiment Classification (Zero-shot)
Output
Positive0.00-1.000.89
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I love my new car. Sentiment:1.000.35-0.01
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.931.00
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The concert was terrible. Sentiment:-1.000.320.06
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.58-0.41
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The show was okay. Sentiment:0.000.45-0.06
Sentiment Classification (Zero-shot)
Output
Neutral0.000.97-1.00
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am very pleased with the outcome. Sentiment:1.000.340.05
Sentiment Classification (Zero-shot)
Output
Positive1.00-0.980.90
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I am upset about the delay. Sentiment:-1.000.31-0.02
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.56-0.37
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: The presentation was mediocre. Sentiment:-1.000.34-0.04
Sentiment Classification (Zero-shot)
Output
Negative-1.00-0.56-0.39
Sentiment Classification (Zero-shot)
Prompt
Classify the text into neutral, negative or positive. Text: I think the vacation is okay. Sentiment:-1.000.38-0.01
Sentiment Classification (Zero-shot)
Output
Neutral-1.000.95-0.96
Hover over data points to inspect them