INDEX

Explanations

conversational phrases

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

Mvh

-1.55

Tja

-1.52

 actrices

-1.51

ฑ

-1.47

 pido

-1.45

 horloge

-1.40

 zimní

-1.40

 arrêter

-1.38

 africaine

-1.36

 élas

-1.34

POSITIVE LOGITS

it

1.55

—

1.38

—

1.30

1.27

</h2>

1.21

all

1.15

and

1.14

but

1.12

Lá

1.09

Activations Density 0.127%