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

Negative Logits

Autoritní

-0.55

ыгана

-0.49

findpost

-0.49

ništ

-0.48

 lenker

-0.47

ftagPool

-0.47

ütfen

-0.46

AndEndTag

-0.46

addCriterion

-0.45

contentLoaded

-0.44

POSITIVE LOGITS

__);

0.55

titas

0.54

 Horowitz

0.53

 الوطنيه

0.52

CloseOperation

0.52

appé

0.51

 NSCoder

0.51

 Distrikt

0.51

 upvote

0.50

 separator

0.49

Activations Density 0.004%

No Known Activations