INDEX

Explanations

occupations and roles

researchers and developers

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

at

1.34

to

1.17

ری

1.17

た

1.15

ش

1.12

ع

1.11

1.09

as

1.07

ت

1.07

س

1.04

POSITIVE LOGITS

’”

0.86

lerce

0.81

li

0.76

 professionnels

0.73

liğini

0.72

preneurs

0.71

锏

0.70

 politici

0.69

 الذين

0.68

 мощности

0.68

Activations Density 0.918%