INDEX

Explanations

introducing new information

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

 then

-1.95

 however

-1.60

 these

-1.45

 furthermore

-1.44

 though

-1.39

もあった

-1.32

 therefore

-1.32

 ausreich

-1.31

jamie

-1.28

弩

-1.27

POSITIVE LOGITS

不一样的

1.28

things

1.13

–

1.11

不一样

1.10

 quello

1.09

found

1.05

名稱

1.05

 taraf

1.05

ίδι

1.03

 grazie

1.02

Activations Density 0.195%