INDEX

Explanations

academic papers and publications

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

 jagged

0.42

撲

0.39

用来

0.39

 pokemon

0.39

 swimming

0.37

 shooting

0.37

 കൂട്ട

0.36

 tingling

0.36

ঁচ

0.36

 cuddling

0.35

POSITIVE LOGITS

 papers

1.39

论文

1.27

論文

1.24

 publication

1.19

 publications

1.19

 paper

1.15

 Papers

1.14

 published

1.08

paper

1.07

papers

1.03

Activations Density 0.011%