INDEX

Explanations

technical terms 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

and

-1.70

taya

-1.45

had

-1.36

for

-1.32

is

-1.32

-1.30

 должна

-1.28

—

-1.21

 должен

-1.16

 району

-1.15

POSITIVE LOGITS

way

1.87



1.80

 verdaderos

1.72

౩

1.71

咴

1.66

 związane

1.64

౯

1.63

阏

1.60

ཿ

1.60

 świecie

1.60

Activations Density 0.082%