INDEX

Explanations

himhispeople trust himwe see him

his/him's

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

它們

0.43

 couples

0.42

它们

0.41

 hogs

0.41

 इनमें

0.40

 remaining

0.40

 horror

0.37

⇆

0.37

walled

0.36

自己

0.36

POSITIVE LOGITS

 அவரை

1.42

 honom

1.33

 그의

1.30

him

1.24

 jego

1.24

 তাঁকে

1.24

 তাকে

1.22

 его

1.18

 ему

1.17

彼の

1.16

Activations Density 0.259%