INDEX

Explanations

Technical/code related texts

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

UnsafeEnabled

-0.59

 BIBSYS

-0.56

saraba

-0.55

ArrowToggle

-0.54

aarrggbb

-0.54

 '\\;'

-0.54

esModule

-0.51

 برانيه

-0.50

 consultato

-0.49

Hozzáférés

-0.49

POSITIVE LOGITS

 Roskov

0.56

 teka

0.51

éez

0.48

Cha

0.48

 تانيه

0.47

DIP

0.47

Cha

0.46

 perdita

0.46

irvana

0.45

 Dues

0.45

Activations Density 0.002%