INDEX

Explanations

I expressing thoughts or actions

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

åĳĬè¯īæĪĳä»¬

-0.11

æĪĳæł¡

-0.10

ä¹Łåıªèĥ½

-0.09

çłļ

-0.09

ä½Ĩä¸įéĻĲäºİ

-0.08

è·ŁæĪĳ

-0.08

è®©æĪĳä»¬

-0.08

æĪĳåĽ½

-0.08

èĢģäººå®¶

-0.08

Sob

-0.08

POSITIVE LOGITS

å¯¹ä»ĸä»¬

0.16

ç»Ļä»ĸä»¬

0.12

å¸®ä»ĸ

0.12

ä¸ºåħ¶

0.11

å¯¹ä»ĸ

0.11

è·Łä»ĸ

0.10

ç»Ļä»ĸ

0.10

å¯¹åħ¶

0.10

è®©ä»ĸä»¬

0.10

è¯ļæĦı

0.10

Activations Density 0.269%