INDEX

Explanations

references to different types of bears

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

 bearing

-1.54

bearing

-1.54

 Bearing

-1.35

 bearings

-1.25

Bearing

-1.23

 Bearings

-0.89

 bearers

-0.62

 specialmente

-0.60

cần

-0.58

 cref

-0.57

POSITIVE LOGITS

 bear

1.66

EndInit

0.85

 Bear

0.76

ukone

0.68

 BEAR

0.67

 bare

0.63

ipot

0.63

Naissance

0.60

ietal

0.60

windowFixed

0.59

Activations Density 0.002%