INDEX

Explanations

code tags and specific structures

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

-1.95

-1.94

all

-1.82

of

-1.73

to

-1.68

by

-1.56

 from

-1.52

one

-1.48

((

-1.47

 voor

-1.39

POSITIVE LOGITS

attendre

1.36

Aceite

1.33

 alcune

1.30

 acolo

1.27

這種

1.26

 ploy

1.25

 duradero

1.24

 Expt

1.23

這麼

1.23

 INVESTIG

1.21

Activations Density 0.000%