INDEX

Explanations

technical terms and arguments

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

ä½ľä¸º

-0.15

 sebagai

-0.15

 jako

-0.14

als

-0.14

kao

-0.12

as

-0.10

 ÐºÐ°ÑĩÐµÑģÑĤÐ²Ðµ

-0.10

yaw

-0.10

 ÏīÏĤ

-0.09

pv

-0.09

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.12

0.10

 Enlight

0.09

éŀ

0.09

 Katrina

0.08

 viable

0.08

acers

0.08

DEX

0.08

 Tactics

0.08

Activations Density 0.227%