INDEX

Explanations

URL components and parameters

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

for

-1.47

-1.37

so

-1.22

-1.15

sa

-1.15

but

-1.15

bo

-1.12

-1.10

 after

-1.10

POSITIVE LOGITS

あー

1.33

もうすぐ

1.28

為に

1.27

 véritables

1.25

 obé

1.24

Leírás

1.23

erkek

1.22

ようで

1.22

 llavero

1.21

iqué

1.21

Activations Density 0.006%