INDEX

Explanations

locations or entities followed by specific words

legal, programming, and technical terms

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

৭০

0.51

ς

0.50

е

0.49

owali

0.48

ρι

0.46

нти

0.46

 système

0.45

ুব

0.45

édie

0.45

تي

0.45

POSITIVE LOGITS

 Ingers

0.44

rails

0.43

 অস্বীকার

0.42

 تعین

0.41

 Ingram

0.41

lips

0.41

 rebels

0.41

 fatta

0.41

UWORD

0.40

 dechlor

0.40

Activations Density 0.001%