INDEX

Explanations

comparisons with than

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

 also

-1.56

ၟ

-1.48

blende

-1.41

ásticas

-1.35

ьому

-1.34

ဴ

-1.33

 parati

-1.33

賎

-1.32

诶

-1.32

annique

-1.30

POSITIVE LOGITS

那种

1.78

 které

1.51

1.50

</u>

1.42

秾

1.38

 Новый

1.36

 (†

1.35

走り

1.26

 ТА

1.25

皺

1.25

Activations Density 0.019%