INDEX

Explanations

code

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

osoba

-0.66

 Dirac

-0.60

+#+

-0.60

بوابة

-0.60

HtmlAttribute

-0.60

 defStyleAttr

-0.59

 papillon

-0.58

 dentelle

-0.57

 kasarigan

-0.56

 margiela

-0.56

POSITIVE LOGITS

 pres

0.63

 Pres

0.53

MLLoader

0.52

pres

0.46

 ingen

0.45

 Paar

0.44

комен

0.42

पया

0.42

par

0.42

openqa

0.42

Activations Density 0.086%