INDEX

Explanations

javascript code keywords

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

 such

-1.54

 that

-1.40

囔

-1.21

 about

-1.18

and

-1.13

 Vortrag

-1.09

 cipolla

-1.08

死者

-1.05

 both

-1.03

gilet

-1.02

POSITIVE LOGITS

кара

1.24

дио

1.17

var

1.17

филь

1.13

are

1.13

we

1.11

фай

1.08

irinha

1.08

return

1.05

 ‘’

1.05

Activations Density 0.016%