INDEX

Explanations

names of people and places

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

 kelapa

-1.42

ಕ

-1.38

moc

-1.35

 wodurch

-1.34

身

-1.34

功效

-1.31

絡

-1.28

 został

-1.27

 invloed

-1.27

gemeester

-1.27

POSITIVE LOGITS

1.82

 alguna

1.59

 некото

1.45

িয়ে

1.43

 SOMETHING

1.41

鋮

1.40

”)

1.37

輾

1.35

ある

1.34

 např

1.34

Activations Density 0.063%