INDEX

Explanations

disapproving and approving

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

 noting

0.51

 indeed

0.48

Indeed

0.43

 জনাব

0.41

 Indeed

0.41

 Noting

0.40

ёд

0.39

 concret

0.38

র্ষণ

0.38

 must

0.38

POSITIVE LOGITS

Times

0.55

Democratic

0.51

said

0.50

 Times

0.50

Acting

0.46

EW

0.46

Apparently

0.46

 said

0.45

 Weekend

0.45

 Approaches

0.45

Activations Density 0.003%