INDEX

Explanations

modification

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 modification

-0.81

 Modification

-0.79

 modifications

-0.78

 Modifications

-0.72

 alteration

-0.58

modific

-0.57

Modifications

-0.57

Modification

-0.55

modification

-0.54

 geme

-0.54

POSITIVE LOGITS

Życiorys

0.58

inheritDoc

0.57

entro

0.54

in

0.53

AutoScaleMode

0.53

сної

0.53

kuuta

0.52

 noqa

0.51

بوابة

0.51

SequentialGroup

0.51

Activations Density 0.026%