INDEX

Explanations

punctuation and list markers

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

↵↵↵↵

0.58

↵↵↵↵↵

0.57

↵↵↵↵↵↵↵↵↵↵↵

0.52

↵↵↵

0.52

↵↵↵↵↵↵↵↵↵↵

0.52

៕

0.49

↵↵↵↵↵↵↵↵

0.48

↵↵↵↵↵↵

0.48

↵↵↵↵↵↵↵

0.48

↵↵

0.43

POSITIVE LOGITS

0.32

ét

0.32

はもちろん

0.32

،

0.31

，

0.30

፣

0.30

”“

0.30

፣

0.29

 université

0.29

උ

0.29

Activations Density 0.074%