INDEX

Explanations

numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 umana

-0.60

 variétés

-0.56

 sanitaires

-0.48

 publiques

-0.47

 vän

-0.47

 blessés

-0.47

 jouets

-0.47

 détruit

-0.47

 leçons

-0.47

 sentiers

-0.47

POSITIVE LOGITS

ind

0.73

AntiForgeryToken

0.61

 invokingState

0.59

 inds

0.59

ртка

0.59

ind

0.59

 lenker

0.57

oneofs

0.56

 Biôgrafia

0.55

IntoConstraints

0.54

Activations Density 0.002%