INDEX

Explanations

bringing about social change

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

ABL

-0.10

 parity

-0.10

 attack

-0.10

 Reform

-0.09

 assault

-0.09

Tre

-0.09

 intellectual

-0.09

 invasion

-0.09

 unity

-0.09

datal

-0.09

POSITIVE LOGITS

 conflicts

0.13

ung

0.12

 grievances

0.12

Conflict

0.12

 Conflict

0.12

ç´

0.11

 Security

0.11

 griev

0.11

 armed

0.11

 conflict

0.11

Activations Density 0.080%