INDEX

Explanations

following 'vv', 'cc', 'KK', 'aaa', 'VV', 'Bb'

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

را

1.45

ra

1.41

การ

1.26

li

1.19

ast

1.17

ล

1.16

}}

1.16

ih

1.16

場合

1.13

ri

1.12

POSITIVE LOGITS

 enjoined

1.57

 recounted

1.57

 expertly

1.56

 carelessly

1.44

 excreted

1.43

 acquitted

1.41

 pozw

1.39

 objected

1.38

 amassed

1.38

 adjudged

1.38

Activations Density 0.000%