INDEX

Explanations

texts attributed to authors or sources

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

 when

-1.63

in

-1.20

you

-1.19

to

-1.18

Sabes

-1.10

 where

-1.05

apatkan

-1.04

when

-1.00

如果您

-1.00

 aña

-0.98

POSITIVE LOGITS

ÁT

1.44

 décider

1.36

by

1.30

 both

1.30

almost

1.22

 Ärz

1.21

 milyen

1.20

.."

1.20

 those

1.20

 довольно

1.18

Activations Density 0.091%