INDEX

Explanations

code comments and declarations

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

が

-1.14

ında

-1.11

を

-1.08

 سپس

-1.07

 проекты

-0.99

 then

-0.97

 Türkei

-0.94

ından

-0.94

Kesimpulan

-0.93

 these

-0.92

POSITIVE LOGITS

 \%$,

0.97

 vermelhas

0.96

xxi

0.95

极

0.95

 bitumen

0.95

を変える

0.94

drž

0.90

laught

0.90

さき

0.90

٣

0.89

Activations Density 0.002%