INDEX

Explanations

scientific paper

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ISBN

-0.13

books

-0.11

Books

-0.10

 Hardcover

-0.10

 ISBN

-0.10

oret

-0.10

 Newsp

-0.10

 Books

-0.10

 Manuals

-0.10

ihan

-0.09

POSITIVE LOGITS

 paper

0.45

 papers

0.37

 article

0.35

paper

0.30

 Paper

0.29

 articles

0.29

-paper

0.28

Paper

0.26

è®ºæĸĩ

0.26

 abstract

0.26

Activations Density 0.210%