INDEX

Explanations

specific labor circumstances

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

 unemployed

-0.12

 occupation

-0.10

 exile

-0.10

ISTR

-0.10

utenberg

-0.09

APER

-0.09

 Rear

-0.09

 Occupation

-0.09

apesh

-0.08

POSITIVE LOGITS

 explo

0.23

 workers

0.23

 worker

0.22

 labor

0.22

 union

0.21

explo

0.21

 sweat

0.21

 exploitation

0.20

 labour

0.20

 Worker

0.17

Activations Density 0.075%