INDEX

Explanations

braw

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

 anglers

-0.69

MLLoader

-0.65

 تانيه

-0.63

IntoConstraints

-0.63

fishing

-0.62

WaitGroup

-0.62

 препратки

-0.61

 embroidered

-0.60

 flashback

-0.59

 dredging

-0.59

POSITIVE LOGITS

halb

0.56

 élas

0.54

 onCreateView

0.52

 cielos

0.52

 సౌకర్య

0.47

 répé

0.47

 européennes

0.46

ect

0.46

windowFixed

0.46

 adicionales

0.45

Activations Density 0.185%