INDEX

Explanations

variable assignments

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

 anything

-1.41

 различ

-1.29

you

-1.20

ところに

-1.18

 effect

-1.16

為に

-1.16

 various

-1.16

 whereas

-1.15

 Fußballspieler

-1.14

 successivamente

-1.13

POSITIVE LOGITS

1.94

は

1.28

Siapa

1.23

}=\

1.20

 pourrait

1.20

 ponemos

1.20

やろ

1.20

というわけで

1.17

 propped

1.17

さんは

1.16

Activations Density 0.019%