INDEX

Explanations

book titles and names

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

-1.74

ଵ

-1.70

ならば

-1.66

ଶ

-1.53

 hivyo

-1.44

andolo

-1.39

的说道

-1.38

 will

-1.38

 muhimu

-1.38

ねば

-1.38

POSITIVE LOGITS

mostly

1.57

Ἰ

1.56

dür

1.54

mainly

1.50

 подрост

1.46

bilden

1.44

亲爱的

1.43

 leão

1.42

 mostly

1.41

ὴν

1.38

Activations Density 0.203%