INDEX

Explanations

content describing rules or examples

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hadley

1.54

 Correspondent

1.27

ळा

1.22

HO

1.20

Þ

1.20

 correspondent

1.15

 Cato

1.14

ï

1.14

 газета

1.13

 находиться

1.13

POSITIVE LOGITS

sef

1.55

klar

1.55

hik

1.52

시다

1.51

bés

1.47

seur

1.47

ug

1.45

ക്ത

1.43

hya

1.41

ৎকার

1.40

Activations Density 0.000%