INDEX

Explanations

fictional characters and proper nouns

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

in

-1.84

 there

-1.83

by

-1.44

no

-1.37

any

-1.36

-1.32

紧接着

-1.31

at

-1.30

 навіть

-1.30

 what

-1.29

POSITIVE LOGITS

 anciennes

1.64

 Dzięki

1.61

 vairāk

1.54

牁

1.54

iſter

1.51

굼

1.50

bagai

1.49

 hôtes

1.47

 vieilles

1.45

kamera

1.44

Activations Density 0.131%