INDEX

Explanations

ress

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

alah

-0.97

 myſelf

-0.71

 themſelves

-0.68

 itſelf

-0.67

 Shakspeare

-0.65

 Fasc

-0.59

 hefyd

-0.59

felves

-0.58

 auffi

-0.58

 himſelf

-0.57

POSITIVE LOGITS

 defStyle

0.52

CrossRef

0.52

 trajets

0.47

MarshalTo

0.47

εια

0.46

iprot

0.46

TUAL

0.46

pad

0.46

 nahilalakip

0.46

mpf

0.45

Activations Density 0.009%