INDEX

Explanations

specific nouns and concepts

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

0.50

，

0.48

。

0.44

0.42

،

0.42

 with

0.39

、

0.37

 without

0.36

에

0.35

POSITIVE LOGITS

 ""))

0.35

ität

0.31

 savent

0.30

人都

0.30

 murderous

0.29

 थांब

0.29

 :");

0.28

 sukar

0.28

sächlich

0.28

 notwend

0.27

Activations Density 0.099%