INDEX

Explanations

user activity and action

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

of

-2.53

and

-1.30

 universitario

-1.27

to

-1.25

НАЯ

-1.16

йтинг

-1.16

 FBref

-1.15

in

-1.09

diator

-1.08

so

-1.07

POSITIVE LOGITS

 themselves

1.54

 their

1.46

 métallique

1.32

jaqueta

1.27

 šaty

1.24

 atentos

1.20

visning

1.20

龗

1.19

 dépasse

1.19

᱘

1.16

Activations Density 0.115%