INDEX

Explanations

English words followed by commas

list item separators

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

֖

0.43

രുദ്ധ

0.42

 listop

0.41

 {}'.

0.40

 sogenannten

0.40

 \%$.

0.39

 {:?}",

0.39

<unused85>

0.39

 paździer

0.38

 właśnie

0.38

POSITIVE LOGITS

、

1.59

、

1.31

1.17

၊

1.14

፣

1.12

-,

1.11

،

1.11

﹑

1.09

1.02

*,

1.00

Activations Density 0.538%