INDEX

Explanations

authority figure

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

odo

-0.11

ists

-0.11

yre

-0.10

-scrollbar

-0.10

ilst

-0.10

yll

-0.10

-0.09

ISTRY

-0.09

store

-0.09

 Barrier

-0.09

POSITIVE LOGITS

 figures

0.17

 authority

0.13

 figure

0.13

/lic

0.12

ship

0.12

 Figures

0.11

figures

0.11

Ð¸ÑĤÐµÑĤ

0.11

ORITY

0.10

itarian

0.10

Activations Density 0.024%