INDEX

Explanations

books and reading

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

ï½¤_

-0.10

 articles

-0.09

warts

-0.09

pam

-0.09

 essays

-0.09

 article

-0.09

æĸĩç«ł

-0.09

 Articles

-0.08

 pamph

-0.08

,ï½¤

-0.08

POSITIVE LOGITS

 reading

0.30

 book

0.29

 Reading

0.26

Reading

0.26

reading

0.25

 Book

0.24

 books

0.23

 library

0.23

Book

0.22

 Books

0.21

Activations Density 0.152%