INDEX

Explanations

evoke cause contribute gauge indulge

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

 provoked

-0.14

 uplift

-0.11

 provoke

-0.10

 attracted

-0.10

 prompted

-0.10

 uplifting

-0.09

 stun

-0.09

bul

-0.09

 attracting

-0.09

 attracts

-0.09

POSITIVE LOGITS

 fuel

0.27

 infl

0.23

 reign

0.22

fuel

0.22

Fuel

0.21

çĩĥ

0.21

 Fuel

0.21

Aw

0.20

 Ð¿ÑĢÐ¾Ð±

0.19

Aw

0.19

Activations Density 0.137%