INDEX

Explanations

model modelbrand and product names

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

 this

-1.69

 gorro

-1.42

 técn

-1.41

 decoracion

-1.41

ſchen

-1.41

ucher

-1.39

 atau

-1.38

guien

-1.37

十几

-1.34

Fakta

-1.33

POSITIVE LOGITS

–

1.55

1.52

 andere

1.48

 anderen

1.37

1.28

1.27

 другие

1.27

躂

1.23

 производство

1.21

着他

1.21

Activations Density 1.625%