INDEX

Explanations

descriptive attributes

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

 stuff

-0.10

 Glory

-0.09

æŁ»

-0.09

Mus

-0.09

amas

-0.09

 close

-0.09

Ar

-0.09

POSITIVE LOGITS

 smile

0.18

 mind

0.16

 heart

0.16

 Smile

0.14

 mission

0.14

 ÑģÐµÑĢÐ´

0.14

 coraz

0.14

plan

0.13

 Appet

0.13

 hearts

0.13

Activations Density 0.071%