INDEX

Explanations

punching, kicking, passing, cooking, gardening

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

anik

-0.09

 coun

-0.09

Wen

-0.09

Us

-0.09

...

-0.09

 switching

-0.08

jog

-0.08

 withholding

-0.08

 impr

-0.08

iner

-0.08

POSITIVE LOGITS

iscing

0.14

angu

0.12

oning

0.11

anch

0.11

asing

0.11

arsing

0.11

ÅĪovÃ¡nÃŃ

0.11

 lawy

0.10

arching

0.10

 merch

0.10

Activations Density 0.117%