INDEX

Explanations

concern for lives and safety

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

开口道

-1.55



-1.54

着一个

-1.51

</b>

-1.50

-1.49

了一口

-1.48

 vérit

-1.45

piecze

-1.44

fatalError

-1.43

haviours

-1.41

POSITIVE LOGITS

 when

1.75

if

1.65

 cuando

1.36

and

1.28

gencias

1.23

↵↵

1.21

的部分

1.20

Стоимость

1.20

when

1.16

普遍

1.16

Activations Density 0.021%