INDEX

Explanations

explicit content and technical terms

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

is

-1.64

in

-1.63

to

-1.45

примеча

-1.35

かというと

-1.33

 Menjadi

-1.32

on

-1.30

was

-1.28

olkata

-1.28

方針

-1.27

POSITIVE LOGITS

and

1.79

↵

1.54

↵↵

1.40

 that

1.31

ほら

1.30

為に

1.30

1.29

 וכן

1.29

)=>{

1.27

 wichtig

1.25

Activations Density 0.001%