INDEX

Explanations

Know

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

новниш

-0.70

tanleria

-0.68

 betweenstory

-0.66

 ivelany

-0.65

 الرياضيه

-0.65

elemField

-0.64

CppMethod

-0.63

 kaarangay

-0.62

Autoritní

-0.61

IntoConstraints

-0.59

POSITIVE LOGITS

0.71

 Know

0.63

Know

0.60

 know

0.59

re

0.56

know

0.56

Ren

0.55

Ren

0.55

 Acknowled

0.55

知

0.54

Activations Density 0.001%