INDEX

Explanations

carriage with horses and driver

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

 Trucks

-0.10

 Truck

-0.10

bik

-0.09

 bunk

-0.09

aeda

-0.09

hunter

-0.09

 Sheep

-0.09

 Seam

-0.08

 Alicia

-0.08

 truck

-0.08

POSITIVE LOGITS

 cart

0.21

 carriage

0.20

 horses

0.19

 horse

0.19

 harness

0.18

 carts

0.18

 coach

0.18

ox

0.17

-cart

0.17

sle

0.17

Activations Density 0.060%