INDEX

Explanations

tribunes are no soldiers; their people

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

tap

-0.10

 Hiro

-0.09

Riv

-0.09

 Vinci

-0.09

 Felipe

-0.09

 protesting

-0.09

enc

-0.08

 denom

-0.08

 Dragons

-0.08

 Patri

-0.08

POSITIVE LOGITS

 trib

0.14

Pub

0.13

 Brut

0.13

 Citizens

0.12

 citizen

0.12

 Tribune

0.12

 Citizen

0.12

 Trib

0.12

mob

0.12

 Capitol

0.11

Activations Density 0.024%