INDEX

Explanations

pol / poly prefixes

pol followed by various endings

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

IBLE

0.40

ა

0.40

σα

0.39

 अत्य

0.39

paired

0.38

:")

0.38

 प्यारे

0.38

 Callback

0.38

 vhodné

0.37

ueba

0.37

POSITIVE LOGITS

Pol

1.00

Pol

0.87

POL

0.84

 पोली

0.84

 поли

0.81

 Polly

0.80

POL

0.79

pol

0.78

Poly

0.77

pol

0.77

Activations Density 0.071%