INDEX

Explanations

interest and choices

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

ä¸ĢäºĽ

-0.26

ä¸Ģç§į

-0.24

ä¸Ģ

-0.23

ä¸ĢåĪĩ

-0.22

ä¸ĢåĢĭ

-0.21

ä¸ĢçĤ¹

-0.19

ä¸Ģå¹´

-0.17

à¸Ħà¸ĵà¸°

-0.16

ä¸Ģçº§

-0.15

ä¸Ģå®ļ

-0.14

POSITIVE LOGITS

 interest

0.24

 Interest

0.20

course

0.19

Interest

0.19

 course

0.18

ft

0.17

interest

0.17

 sorts

0.17

 choice

0.16

_interest

0.16

Activations Density 0.149%