INDEX

Explanations

prepositions followed by nouns

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

鲧

-1.42

 other

-1.30

做法

-1.29

方法

-1.26

 eſſ

-1.25

oció

-1.23

Xem

-1.23

who

-1.23

\\\

-1.20

٪

-1.20

POSITIVE LOGITS

 allow

1.44

了我

1.22

 allows

1.20

 могла

1.20

 during

1.19

 permits

1.18

 слишком

1.17

 jaką

1.16

During

1.15

太多

1.14

Activations Density 0.504%