INDEX

Explanations

more sophisticated, nonsensical

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

¹,

1.59

¹.

1.43

 गटा

1.42

 Compar

1.42

●

1.40

●

1.33

➢

1.33



1.33

⇢

1.32

跟

1.29

POSITIVE LOGITS

chyn

1.30

お待ち

1.25

cerr

1.21

acek

1.16

هداف

1.15

ustes

1.15

விழ

1.15

 Maharaj

1.14

वस्था

1.13

iselle

1.12

Activations Density 14.049%