INDEX

Explanations

proper nouns and numbers

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

to

-1.13

 still

-1.12

などなど

-1.08

we

-1.06

における

-1.04

 Like

-1.02

 文章

-1.02

 like

-1.00

by

-0.99

 Because

-0.99

POSITIVE LOGITS

 servicios

1.26

íná

1.18

ကိုးက

1.18

 admon

1.15

ְּ

1.14

 ルーム

1.13

legte

1.13

Www

1.13

ptime

1.13

 verhaal

1.13

Activations Density 0.003%