INDEX

Explanations

first published

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

è¨ĺäºĭ

-0.11

æĿ¥èĩª

-0.10

ixe

-0.10

ossier

-0.09

urer

-0.09

Created

-0.09

 papers

-0.09

ique

-0.08

Authors

-0.08

æĸĩçĮ®

-0.08

POSITIVE LOGITS

 published

0.30

published

0.23

 Published

0.23

Published

0.22

 publication

0.20

pub

0.20

 publish

0.20

pub

0.19

ublished

0.18

 publi

0.18

Activations Density 0.135%