INDEX

Explanations

man, woman, person, people

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

Participant

-0.68

 maestros

-0.68

тики

-0.68

철

-0.67

atschapp

-0.66

็ก

-0.66

NF

-0.65

lorin

-0.65

lím

-0.65

AMAR

-0.65

POSITIVE LOGITS

men

3.06

woman

2.89

man

2.52

women

2.52

persons

1.94

WOMAN

1.86

person

1.76

MAN

1.70

mens

1.70

MEN

1.68

Activations Density 0.053%