INDEX

Explanations

describing nuance

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tragedy

1.36

 stimulant

1.17

 influential

1.16

 commodity

1.16

 revolutionary

1.16

 calamity

1.16

 contributor

1.15

 comedian

1.14

 reactionary

1.13

 thing

1.13

POSITIVE LOGITS

各自

1.09

它们的

0.94

 đều

0.89

们的

0.85

неш

0.84

ทุกคน

0.84

 зовніш

0.82

 सरकारों

0.82

ombres

0.80

들은

0.78

Activations Density 0.275%