INDEX

Explanations

no longer

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

ä»İæĿ¥

-0.11

ä¸ĢçĽ´ä»¥æĿ¥

-0.11

éķ¿æľŁä»¥æĿ¥

-0.11

è¿Ħä»Ĭä¸ºæŃ¢

-0.11

è¿Ħä»Ĭ

-0.10

åİĨæĿ¥

-0.10

æŃ¤æ¬¡

-0.10

UGH

-0.10

 currently

-0.10

çĽ®åīį

-0.09

POSITIVE LOGITS

ä¸įåĨįæĺ¯

0.22

ä¸įåĨį

0.20

åĨįä¹Łä¸į

0.18

ä¸įä¼ļåĨį

0.15

 artÄ±k

0.14

åĨįä¹Łæ²¡æľī

0.13

åĨįä¹Ł

0.13

ä¸įèĥ½åĨį

0.12

ãĤĪãģĨãģ«ãģªãĤĬãģ¾ãģĹãģŁ

0.12

æĵį

0.12

Activations Density 0.159%