INDEX

Explanations

algebraic structure

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

 Monte

-0.13

ed

-0.11

le

-0.10

cop

-0.10

 mont

-0.10

 Mont

-0.10

ampoline

-0.10

 Caesar

-0.10

 Lucas

-0.10

Mont

-0.10

POSITIVE LOGITS

 Hitch

0.12

ä»£

0.11

-top

0.11

EGA

0.11

 obstruction

0.11

 topology

0.11

/top

0.11

Mum

0.11

 Functor

0.10

 obstruct

0.10

Activations Density 0.044%