INDEX

Explanations

function documentation and steps

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

leans

-0.09

Verdana

-0.09

 ########.

-0.09

anou

-0.09

ãĥ³ãĥĶ

-0.09

edback

-0.08

.getConfig

-0.08

olor

-0.08

 dÃŃl

-0.08

 pairwise

-0.08

POSITIVE LOGITS

 demean

0.10

toy

0.10

 recovered

0.10

recover

0.09

 Sans

0.09

 recover

0.09

 perplex

0.09

toy

0.09

alog

0.09

æ±Ĺ

0.09

Activations Density 0.062%