INDEX

Explanations

any object or abstract quality

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

or

-1.88

it

-1.70

at

-1.57

and

-1.57

so

-1.43

 like

-1.40

izzling

-1.38

ceptre

-1.38

by

-1.36

 slika

-1.36

POSITIVE LOGITS

 этих

1.30

 trône

1.22

 começo

1.21

 estavam

1.20

もありますが

1.19

↵↵↵

1.18

опера

1.18

谆

1.16

]["

1.15

 fût

1.14

Activations Density 0.209%