INDEX

Explanations

numbers starting with 0

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

 próximo

-1.48

 próxima

-1.30

に行ってきました

-1.16

جرة

-1.16

 decentralized

-1.16

 Rückkehr

-1.14

 खोज

-1.13

.(

-1.13

cambrian

-1.13

님

-1.12

POSITIVE LOGITS

 rette

1.41

 bluse

1.38

 いる

1.36

lijden

1.32

КИ

1.31

 Arkivert

1.30

 '/';

1.28

ന

1.27

 chini

1.27

 hilsen

1.27

Activations Density 0.121%