INDEX

Explanations

code comments 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

襁

-1.30

begins

-1.30

𝘋

-1.21

 these

-1.16

 клини

-1.10

に入れる

-1.10

Pozri

-1.10

 öst

-1.09

 TYPES

-1.06

indicated

-1.06

POSITIVE LOGITS

がある

1.41

もある

1.38

in

1.22

 pioggia

1.20

 which

1.13

 JMenuItem

1.10

廼

1.10

If

1.10

デメリット

1.07

と思っている

1.06

Activations Density 0.019%