INDEX

Explanations

distances and dimensions

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

leyin

-1.27

komme

-1.22

unser

-1.12

 capuche

-1.10

 kaž

-1.10

opheles

-1.07

alties

-1.03

 magasiner

-1.02

diese

-1.02

 endwhile

-1.02

POSITIVE LOGITS

 another

1.34

 nuevamente

1.23

 again

1.16

一小

1.09

mal

1.09

zek

1.01

気分

1.01

man

1.01

par

0.99

 nochmals

0.99

Activations Density 0.004%