INDEX

Explanations

past tense verbs

phrases changed or removed

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 থাকে

0.76

 असतो

0.76

 असतात

0.73

 იქნება

0.73

됩니다

0.73

 आहेत

0.71

 ہے

0.70

 हैं

0.69

 είναι

0.69

 ہیں۔

0.67

POSITIVE LOGITS

 gave

2.36

 took

2.30

took

2.16

 went

2.11

gave

2.06

wrote

1.88

 drove

1.82

 wrote

1.80

Took

1.79

did

1.78

Activations Density 0.718%