INDEX

Explanations

commented distributed text

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

 ASSETS

-0.78

driving

-0.73

境的

-0.73

 sanity

-0.70

 rectangle

-0.69

 Berechnung

-0.69

TryGetValue

-0.68

knows

-0.67

tamin

-0.66

achieve

-0.66

POSITIVE LOGITS

aken

0.73

Preferred

0.73

 Sira

0.70

bruik

0.67

 dungeons

0.66

 deputies

0.66

SelectedIndex

0.65

ifferentiated

0.65

Format

0.65

På

0.65

Activations Density 0.044%