INDEX

Explanations

proposed

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

 nahilalakip

-0.70

 BorderSide

-0.57

 lenker

-0.56

//

-0.55

tagHelperRunner

-0.54

timacy

-0.54

windowFixed

-0.54

 beginnetje

-0.54

 باخ

-0.53

haled

-0.53

POSITIVE LOGITS

:✨

0.50

 establishments

0.50

new

0.49

 changes

0.48

tative

0.47

 modifications

0.47

UnsafeEnabled

0.47

Erreferentziak

0.47

 means

0.46

 institutions

0.46

Activations Density 0.003%