INDEX

Explanations

the tokens "pure" and "bloody", particularly when capitalized

pure

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

pyplot

-0.46

総

-0.46

 quelqu

-0.46

 ympä

-0.45

 fidanz

-0.44

 незавершена

-0.42

 raffredd

-0.42

 scolaires

-0.41

rę

-0.41

 kayna

-0.41

POSITIVE LOGITS

 Startseite

0.60

 onData

0.60

참고

0.60

bred

0.60

 Vikipedi

0.59

MessageOf

0.59

лактика

0.59

LEncoder

0.57

hells

0.57

 plurality

0.56

Activations Density 1.165%