INDEX

Explanations

academic citations and years

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

۱۳

0.30

۱۰

0.27

Screenshot

0.26

 १३

0.26

 지난해

0.25

ுமி

0.25

 ২০১৭

0.25

ネイ

0.25

תי

0.25

 ۱۳

0.25

POSITIVE LOGITS

of

0.33

os

0.28

 mediated

0.28

by

0.27

ide

0.25

 killings

0.25

for

0.25

arg

0.24

ol

0.24

ug

0.24

Activations Density 0.000%