INDEX

Explanations

red

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

LookAnd

-0.84

 BoxDecoration

-0.83

GEBURTSDATUM

-0.82

AndEndTag

-0.77

IntoConstraints

-0.72

UnusedPrivate

-0.71

 Wiktionnaire

-0.71

Rüyada

-0.70

rungsseite

-0.69

 SearchView

-0.68

POSITIVE LOGITS

red

0.51

 Formed

0.46

 formed

0.43

He

0.41

 rød

0.40

 white

0.40

BM

0.39

 červen

0.37

 włos

0.36

ered

0.36

Activations Density 0.000%