INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nakalista

-0.77

 архивлан

-0.77

 ligiloj

-0.73

keeps

-0.71

takes

-0.71

 nahilalakip

-0.71

 nonUne

-0.70

();)

-0.70

 Italijani

-0.70

 européennes

-0.70

POSITIVE LOGITS

 think

0.42

 Comcast

0.41

XDECREF

0.41

WriteLiteral

0.38

 likely

0.37

 stop

0.36

 thing

0.35

========

0.34

agnos

0.34

Carmen

0.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.