INDEX

Explanations

snowboard or ski

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

 Stard

-0.10

Sle

-0.10

 Archer

-0.09

 Graz

-0.09

 Ness

-0.09

 Moor

-0.09

 Chain

-0.09

 Thorn

-0.09

 saddle

-0.09

 Bund

-0.09

POSITIVE LOGITS

 bindings

0.16

 powder

0.16

 Powder

0.15

sk

0.14

bindings

0.14

Bindings

0.13

Pow

0.13

 resort

0.12

 binding

0.12

 Binding

0.12

Activations Density 0.004%