INDEX

Explanations

for the first time

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

æ¶§

-0.09

çīĮ

-0.09

eki

-0.09

çĭ¡

-0.09

etta

-0.08

å½ĵäºĭ

-0.08

adget

-0.08

è¯Ī

-0.08

å¹²ä»Ģä¹Ī

-0.08

ifiers

-0.08

POSITIVE LOGITS

ç¬¬ä¸Ģæ¬¡

0.25

é¦ĸæ¬¡

0.24

åīįæīĢæľª

0.18

åīįæīĢæľªæľī

0.18

åĪĿãĤģãģ¦

0.18

Ð¿ÐµÑĢÐ²

0.16

 ì²ĺìĿĮ

0.16

åĪĿæ¬¡

0.15

 láº§n

0.14

åĨįä¹Ł

0.12

Activations Density 0.116%