INDEX

Explanations

question words in multiple languages

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

Ꮵ

-1.43

 diskusi

-1.42

 також

-1.41

푆

-1.38

 ソックス

-1.38

鼇

-1.32



-1.31

bluza

-1.30

ครื่อง

-1.29

 maky

-1.29

POSITIVE LOGITS

 else

2.08

1.95

になれば

1.52

béco

1.33

do

1.29

 entendi

1.22

 tore

1.17

 vengono

1.16

 proches

1.15

 же

1.14

Activations Density 0.008%