INDEX

Explanations

first

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

éļħ

-0.11

æ¦ķ

-0.10

æĴĳ

-0.10

çŁ³çģ°

-0.09

èĥ¸æĢĢ

-0.09

èĢģäººå®¶

-0.09

ä»»ä½ķäººéĥ½

-0.09

æĬĬèĩªå·±çļĦ

-0.09

åĴĶ

-0.09

éĢĤåĲĪèĩªå·±

-0.09

POSITIVE LOGITS

ç¬¬ä¸Ģæ¬¡

0.18

é¦ĸæ¬¡

0.16

åĪĿæ¬¡

0.13

ç¬¬ä¸īæ¬¡

0.13

åĪĿãĤģãģ¦

0.13

ç¬¬äºĮæ¬¡

0.12

 láº§n

0.11

åīįæīĢæľª

0.10

 isFirst

0.10

è¿Ļæ¬¡

0.10

Activations Density 0.151%