INDEX

Explanations

if not

even different languages

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

 ਕੇ

0.44

0.41

še

0.40

achio

0.40

hte

0.38

ře

0.38

ვით

0.37

ണ്ണി

0.37

 kože

0.37

玮

0.36

POSITIVE LOGITS

 voire

1.79

甚至是

1.78

甚至

1.68

乃至

1.58

 thậm

1.38

 bahkan

1.26

 hatta

1.26

 혹은

1.20

 или

1.18

もしくは

1.16

Activations Density 0.119%