INDEX

Explanations

Howe

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

theless

-0.63

ificantly

-0.62

ʖ

-0.59

etheless

-0.57

 تانيه

-0.54

ijuana

-0.53

xiety

-0.53

foundland

-0.53

nipeg

-0.52

faßt

-0.52

POSITIVE LOGITS

openzeppelin

0.65

ModelAdmin

0.56

off

0.48

twimg

0.48

 pulumi

0.47

balleur

0.47

ttet

0.46

ollectionView

0.46

graphicx

0.45

WillAppear

0.44

Activations Density 0.001%