INDEX

Explanations

training

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

centages

-0.73

adays

-0.71

ian

-0.69

ists

-0.68

ities

-0.67

tening

-0.66

'],

-0.66

"},

-0.66

imum

-0.65

 pearls

-0.65

POSITIVE LOGITS

 publiques

0.67

0.56

 juridiques

0.47

Davide

0.46

ی

0.45

 financières

0.44

 hauts

0.43

 culturelles

0.43

 تعدى

0.42

Anmerkungen

0.41

Activations Density 0.167%