INDEX

Explanations

writing X, had to X, relocate to X

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

 již

-1.61

非常的

-1.38

是非常

-1.37

 whilst

-1.34

 כאשר

-1.33

 skall

-1.31

ですので

-1.26

 monies

-1.21

🏏

-1.19

な感じ

-1.16

POSITIVE LOGITS

 żeby

1.50

—

1.30

 разных

1.26

nadequate

1.23

里的

1.23

ernalia

1.21

pplung

1.19

nie

1.18

 impos

1.17

めちゃくちゃ

1.16

Activations Density 0.110%