INDEX

Explanations

you want to

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

 Wagner

-0.10

 Vend

-0.10

èİ«

-0.10

 gonna

-0.10

wan

-0.09

atura

-0.09

IRR

-0.08

 Clair

-0.08

ought

-0.08

 thirst

-0.08

POSITIVE LOGITS

 want

0.16

 muá»ĳn

0.16

 wants

0.16

 wanted

0.16

 ingin

0.14

Ø±ÙĬØ¯

0.13

à¹īà¸Ńà¸ĩà¸ģà¸²à¸£

0.13

 wish

0.13

è¦ģ

0.12

 ÑħÐ¾ÑĤ

0.11

Activations Density 0.037%