INDEX

Explanations

polite particles and question endings

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

Вот

-0.78

dann

-0.77

conform

-0.77

შ

-0.76

 conden

-0.75

 nombre

-0.74

 chargers

-0.73

近年来

-0.73

んですよね

-0.72

でしたね

-0.71

POSITIVE LOGITS

po

1.99

です

1.98

ค่ะ

1.54

ครับ

1.44

Po

1.33

 lang

1.30

 nhé

1.29

Po

1.23

ạ

1.16

Lang

1.14

Activations Density 0.030%