INDEX

Explanations

"CO", "ID", "name", "track", "selection", "catalogue"

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

 Automó

-1.40

 what

-1.38

 Senado

-1.37

 americano

-1.36

 dager

-1.33

开来

-1.31

jadikan

-1.30

：

-1.29

 какво

-1.28

！！！！！

-1.28

POSITIVE LOGITS

 REALLY

1.19

ykjav

1.18

 전체

1.17

 praticamente

1.15

 также

1.12

 essas

1.11

嚷

1.09

 búsquedas

1.06

 装修

1.06

 molte

1.06

Activations Density 0.004%