INDEX

Explanations

descriptors followed by nouns

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.81

 срока

-1.30



-1.27



-1.24



-1.23

央视

-1.20

ambut

-1.16

andere

-1.16

 станет

-1.16

艹

-1.14

POSITIVE LOGITS

che

1.47

 IBOutlet

1.31

if

1.28

 more

1.23

 auffi

1.23

 greater

1.22

给他

1.22

 جيدة

1.21

 further

1.21

 utafiti

1.18

Activations Density 0.064%