INDEX

Explanations

for your

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

 Yours

-0.13

 oneself

-0.12

 ourselves

-0.10

ours

-0.10

à¸Ĥà¸Ńà¸ĩà¸ľ

-0.10

@brief

-0.10

 theirs

-0.09

amilia

-0.09

 iddi

-0.09

OURS

-0.09

POSITIVE LOGITS

 your

0.46

ä½łçļĦ

0.35

your

0.33

 Ð²Ð°ÑĪ

0.31

Your

0.28

 votre

0.26

 Your

0.25

æĤ¨çļĦ

0.23

 à¤Ĩà¤ªà¤ķ

0.22

tuo

0.22

Activations Density 0.145%