INDEX

Explanations

actions and subsequent states

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

 السياس

-1.68

Musik

-1.28

 жизнь

-1.24

Irlande

-1.23

ovým

-1.22

ּוֹ

-1.21

ִּ

-1.19

 Kompon

-1.16

 démocr

-1.16

ができます

-1.16

POSITIVE LOGITS

𝑈

1.44

('/:

1.28

 feminino

1.27

 پروفایل

1.23

 progresso

1.21

 this

1.17

 cavalo

1.17

 بدأ

1.08

("/:

1.08

今回は

1.08

Activations Density 0.043%