INDEX

Explanations

numbers after slashes

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

 also

-1.85

ございました

-1.63

 entsprechenden

-1.58

そうですが

-1.52

 большинстве

-1.49

It

-1.47

 entspre

-1.46

Also

-1.45

的相关

-1.42

rador

-1.41

POSITIVE LOGITS

who

1.55

：

1.41

↵↵

1.32

由

1.27

1.25

idk

1.24

 "..\..\

1.23

archiwizowane

1.23

 about

1.22

 neko

1.22

Activations Density 0.053%