INDEX

Explanations

conditions and contrasts

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

indsight

-0.09

 Icons

-0.09

 finally

-0.09

arness

-0.08

theValue

-0.08

ldkf

-0.08

vyk

-0.08

 Finally

-0.08

 Mens

-0.08

POSITIVE LOGITS

 traditional

0.19

 conventional

0.18

 when

0.18

 When

0.17

 Traditional

0.15

When

0.15

 modern

0.14

when

0.14

 normal

0.13

Traditional

0.13

Activations Density 0.192%