INDEX

Explanations

names and titles of leaders

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

 estructural

-0.83

ḳ

-0.77

ਖ਼

-0.73

煒

-0.72

autonomie

-0.72

structural

-0.71

ぁ

-0.69

 structural

-0.69

 measles

-0.68

chris

-0.68

POSITIVE LOGITS

 Churchill

3.59

 Winston

3.38

Winston

2.92

Church

2.58

 CHURCH

2.05

 Church

1.82

FDR

1.73

CHURCH

1.73

winston

1.70

 Roosevelt

1.65

Activations Density 0.045%