INDEX

Explanations

need to perform an action

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

 到着

-1.63

 ścian

-1.52

،

-1.49

而言

-1.44

-1.43

 góry

-1.42

 odleg

-1.40

 satisfaire

-1.39

 better

-1.39

อาจ

-1.38

POSITIVE LOGITS

in

1.67

你来

1.49

خابات

1.48

ícias

1.45

 there

1.43

by

1.41

ಠ

1.38

once

1.37

 作り方

1.36

 However

1.34

Activations Density 0.057%