INDEX

Explanations

model response marker

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

ла

1.47

า

1.38

lng

1.27

lere

1.23

lio

1.18

tion

1.18

ate

1.16

manship

1.15

lara

1.15

POSITIVE LOGITS

亠

1.13

()=>{

1.06

이다

1.05

oed

1.04

쭌

0.98

RegisterClass

0.95

秙

0.95

 absol

0.95

 poter

0.94

 directs

0.93

Activations Density 0.295%