INDEX

Explanations

punctuation, and non-English characters

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

 centrally

-0.23

æºľ

-0.23

ç»ĪçĶŁ

-0.22

uide

-0.22

æŁ¥

-0.22

 himself

-0.22

ä¹Łæĺ¯éĿŀå¸¸

-0.21

çĬĬ

-0.21

ç®į

-0.21

 clar

-0.20

POSITIVE LOGITS

åŀĦæĸŃ

0.28

æĹ¶å¸¸

0.28

å¦Ħ

0.25

ä¾µçĬ¯

0.24

è¯´æĪĳ

0.24

 ruining

0.24

å¹²æī°

0.24

 infuri

0.24

ä¾µå®³

0.23

éĢ¼

0.23

Activations Density 0.102%