INDEX

Explanations

groups of people and their communities

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 Responsible

0.40

naments

0.38

responsible

0.38

 посвящен

0.38

うえ

0.38

 seduced

0.37

Logged

0.37

prache

0.37

 уя

0.37

 Setup

0.37

POSITIVE LOGITS

американ

0.43

 Americans

0.42

 disproportion

0.41

 https

0.41

 systematic

0.40

 Amerika

0.39

steil

0.39

 Америки

0.38

裔

0.38

 comunità

0.38

Activations Density 0.013%

No Known Activations