INDEX

Explanations

also followed by a word

also followed by descriptive listing words

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

 também

0.39

 også

0.37

 also

0.36

 myös

0.35

 Also

0.35

 भी

0.35

 επίσης

0.35

 También

0.34

 aussi

0.34

 también

0.33

POSITIVE LOGITS

ledes

0.26

 нередко

0.25

 чаще

0.25

৬

0.25

 имеет

0.24

 불구하고

0.24

\"{

0.24

 существенно

0.24

显得

0.24

iswa

0.23

Activations Density 0.325%