INDEX

Explanations

motifs

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

ography

-0.84

lography

-0.84

yship

-0.79

RenderAtEndOf

-0.77

nastics

-0.77

énario

-0.76

ergies

-0.76

kosh

-0.76

الحياه

-0.75

 Roskov

-0.75

POSITIVE LOGITS

 asmen

0.45

parc

0.43

 unstable

0.42

pumpe

0.41

 easier

0.41

 semn

0.41

enso

0.40

ondi

0.40

hofen

0.40

old

0.40

Activations Density 0.100%