INDEX

Explanations

match specific conditions

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

arness

-0.09

opes

-0.09

 ï½°

-0.09

 adequ

-0.09

 fore

-0.08

 à¸Ħà¸¥

-0.08

Hint

-0.08

elli

-0.08

 Gloria

-0.08

POSITIVE LOGITS

 match

0.16

 contain

0.14

 contained

0.13

 matches

0.12

match

0.11

 whose

0.11

åĮ¹

0.10

 mach

0.10

contain

0.10

 have

0.10

Activations Density 0.116%