INDEX

Explanations

lists of things and people

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

 السلط

0.25

主要

0.25

AUTHOR

0.24

 industrialists

0.24

HIGHLIGHT

0.24

ربة

0.23

 пода

0.23

 bureaucrats

0.23

 displayNumber

0.23

くだ

0.23

POSITIVE LOGITS

dur

0.33

followed

0.33

 oppure

0.31

derr

0.29

 debated

0.29

 held

0.29

 यामुळे

0.29

 followed

0.28

enn

0.28

 dismay

0.28

Activations Density 0.003%