INDEX

Explanations

technical nouns and roles

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

''

-1.28

 作り方

-1.24

從

-1.21

＿＿

-1.20

Obsah

-1.20

Zdra

-1.16

こんばん

-1.15

雰囲

-1.15

During

-1.15

 炒め

-1.13

POSITIVE LOGITS

 that

1.84



1.34

 option

1.27

也是

1.27

入了

1.26

 именно

1.23

就可以了

1.20

…

1.19

 wasn

1.17

किन

1.16

Activations Density 0.137%