INDEX

Explanations

traceback most recent call last

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

 forward

-0.68

 Forward

-0.67

螢

-0.66

cierge

-0.65

Clearing

-0.63

 fail

-0.62

 dolci

-0.61

 support

-0.61

Updating

-0.60

updating

-0.60

POSITIVE LOGITS

чиков

0.85

 wiesz

0.77

outchou

0.77

uminate

0.73

parseLong

0.70

ліза

0.70

 Thine

0.70

畴

0.69

tund

0.69

adari

0.68

Activations Density 0.075%