INDEX

Explanations

self-representation or self-activation

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

æļ´

-0.12

çĪĨ

-0.09

å·¡åĽŀ

-0.09

æīĺ

-0.09

æīĺç®¡

-0.09

æĺĻ

-0.09

åīįæīĢ

-0.09

å½ª

-0.08

éĢĢ

-0.08

 eBook

-0.08

POSITIVE LOGITS

ä¸ºèĩªå·±

0.16

ç»Ļèĩªå·±

0.16

å¯¹èĩªå·±

0.15

èĩªèº«

0.15

èĩªæĪĳ

0.14

self

0.14

å¯¹èĩªå·±çļĦ

0.14

èĩªå¸¦

0.14

èĩªè¡Į

0.14

 self

0.14

Activations Density 0.270%