INDEX

Explanations

structure and formation

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

música

-1.72

⽼

-1.70

vertre

-1.64

⼥

-1.62

Produits

-1.59

ḿ

-1.59

("\

-1.57

Jegy

-1.55

unuz

-1.51

 farine

-1.51

POSITIVE LOGITS

all

1.63

but

1.49

 wideo

1.37

將軍

1.33

 Substanz

1.30

inheritDoc

1.26

 stránky

1.25

moi

1.23

…..

1.23

 przycis

1.23

Activations Density 0.036%