INDEX

Explanations

interface, increasing acceptance

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

-1.19

 Even

-1.14

-1.13

 unrelenting

-1.09

go

-1.08

re

-1.08

 tiny

-1.08

 make

-1.07

-1.05

How

-1.02

POSITIVE LOGITS

 jezt

1.27

킁

1.27

 ジップ

1.23

 ポーチ

1.21

 Infór

1.20

zwi

1.20

honestly

1.19

every

1.18

 ſeveral

1.16

 białym

1.16

Activations Density 0.002%