INDEX

Explanations

you followed by a verb

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

其他

0.78

什么样的

0.76

那些

0.75

 שלא

0.73

 לאחר

0.73

 איך

0.73

任何

0.70

 аз

0.70

 ну

0.69

การ

0.69

POSITIVE LOGITS

are

1.62

 have

1.49

 êtes

1.47

 avez

1.27

 were

1.17

 HAVE

1.15

 hebben

1.14

 tienes

1.13

 είναι

1.12

 estão

1.11

Activations Density 0.604%