INDEX

Explanations

abbreviations or single letters ending sentences

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

an

1.93

у

1.38

ع

1.37

 público

1.35

ા

1.31

bbero

1.28

])

1.26

า

1.24

ן

1.22

inom

1.16

POSITIVE LOGITS

 steeper

1.28

st

1.21

к

1.18

ਇ

1.15

нига

1.14

soever

1.12

近年来

1.10

 hoạt

1.10

 IBOutlet

1.10

 ditentukan

1.10

Activations Density 0.087%