INDEX

Explanations

a component or device description

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

футболка

-1.70

、

-1.66

炻

-1.48

ются

-1.42

it

-1.40

 pittore

-1.40

ۓ

-1.39

这是

-1.38

 gekocht

-1.38

POSITIVE LOGITS

⚋

1.60

lielmo

1.57

辚

1.50

⢪

1.49

 nahm

1.49

 inconsciente

1.48

峮

1.46

ครื่อง

1.46

1.44

romy

1.43

Activations Density 0.047%