INDEX

Explanations

names of countries and regions

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

 American

-1.10

US

-0.98

American

-0.93

 Canadian

-0.93

 Australian

-0.84

US

-0.82

 Amerikaanse

-0.82

Canadian

-0.81

 american

-0.79

Australian

-0.74

POSITIVE LOGITS

 Russia

1.33

+#+#

1.31

 Italy

1.30

 Poland

1.25

 CHINA

1.25

Russia

1.24

 Ireland

1.22

 ITALY

1.21

 russia

1.20

 China

1.19

Activations Density 0.355%