INDEX

Explanations

referring to something

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

}$.

-1.58

he

-1.49

</b>

-1.40

冶

-1.39

of

-1.38

 parfois

-1.38

quirer

-1.34

 mondta

-1.32

 reconocida

-1.29

itação

-1.27

POSITIVE LOGITS

كيفية

1.49

夘

1.47

 someone

1.45

他有

1.44

 którzy

1.43

 carico

1.42

alties

1.41

any

1.40

Gön

1.39

 somebody

1.38

Activations Density 0.041%