INDEX

Explanations

Korea and Japan

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

 Notable

-0.70

Notable

-0.70

 Freizeit

-0.69

 资料

-0.69

 phosph

-0.68

Ulu

-0.68

Mai

-0.67

 लो

-0.65

 Kanada

-0.65

Chen

-0.65

POSITIVE LOGITS

 Korea

1.21

 Korean

1.11

 korean

1.01

 Seoul

0.98

 Pyongyang

0.93

Seoul

0.91

 Japan

0.91

 Busan

0.91

 Koreans

0.90

 Corée

0.88

Activations Density 0.070%