INDEX

Explanations

good

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

contentLoaded

-0.70

 kaarangay

-0.63

 BoxFit

-0.62

 Biôgrafia

-0.61

protoimpl

-0.59

 PopupWindow

-0.59

 oprot

-0.58

 Roskov

-0.57

 Vikipedi

-0.55

ografija

-0.55

POSITIVE LOGITS

 good

1.13

good

0.88

Good

0.73

 Good

0.70

 GOOD

0.68

 buena

0.67

 goede

0.65

GOOD

0.63

 gute

0.60

 buenas

0.60

Activations Density 0.001%