INDEX

Explanations

Normandy's industry and resistance

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

 wartime

-0.15

 frontier

-0.09

æģ

-0.09

 Lakes

-0.09

 Mant

-0.09

 Svens

-0.09

 cavalry

-0.09

 missile

-0.09

ewart

-0.08

Voy

-0.08

POSITIVE LOGITS

 Norm

0.36

 landing

0.31

Norm

0.27

 Landing

0.26

 norm

0.25

 beach

0.21

landing

0.21

norm

0.21

 beaches

0.21

 landed

0.21

Activations Density 0.025%