INDEX

Explanations

certain followed by a noun

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

æŁŀ

-0.10

otel

-0.09

éļ¾å¾Ĺ

-0.08

åıĹå®³

-0.08

vic

-0.08

çļĦå¯¹è±¡

-0.08

åĭŁèµĦ

-0.08

ennon

-0.08

åıĹå®³èĢħ

-0.08

such

-0.08

POSITIVE LOGITS

 certain

0.12

 Certain

0.10

æŁĲäºĽ

0.10

æŁĲ

0.10

çŃļ

0.10

æ¨ª

0.09

Certain

0.09

åĸĦäºİ

0.09

åħ·æľīä¸Ģå®ļ

0.08

imiter

0.08

Activations Density 0.062%