INDEX

Explanations

lists with "and" or "&"

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

(),

0.93

…)

0.86

 altogether

0.83

 intravenously

0.80

 också

0.80

())

0.78

,(

0.75

0.74

…

0.72

...(

0.72

POSITIVE LOGITS

amp

1.84

mdash

1.37

ndash

1.32

quot

1.25

ldquo

1.25

middot

1.13

nbsp

1.09

raquo

1.06

amp

1.06

apos

1.04

Activations Density 0.476%