INDEX

Explanations

professions or roles followed by speech

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

é«ĺçŃīåŃ¦æł¡

-0.08

Ð·Ð¼

-0.08

å¯¹èĩªèº«

-0.07

èĩªèº«ãģĮ

-0.07

æĥ³èĳĹ

-0.07

è®¤ä¸ºèĩªå·±

-0.07

 consistently

-0.07

åĲĦçº§åħļå§Ķ

-0.07

é¸³

-0.07

çĽ´æİ¥æĪĸéĹ´æİ¥

-0.07

POSITIVE LOGITS

 ÙĤØ±ÙĨ

0.08

æĭ¿æĿ¥

0.08

adle

0.08

å®īæİĴ

0.08

egov

0.07

essler

0.07

æĦıåĳ³

0.07

åħģè®¸

0.07

 allowed

0.07

allowed

0.06

Activations Density 0.225%

No Known Activations