INDEX

Explanations

few people, things, or instances

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

噚

-1.51

 reinigen

-1.44

consulté

-1.41

-1.40

ükü

-1.39

футбо

-1.38

ваку

-1.37

 défi

-1.37

 tournoi

-1.37

день

-1.35

POSITIVE LOGITS

 forms

1.54

 guarantees

1.47

’

1.42

及其

1.40

谁能

1.37

示意图

1.36

few

1.35

を行い

1.34

(<

1.34

 attain

1.34

Activations Density 0.021%