INDEX

Explanations

a a a a a a a a a a good good

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

:::::

-0.09

Ã¤tz

-0.09

 chops

-0.09

 Candid

-0.09

ernaut

-0.09

áº«

-0.09

evi

-0.08

-thumb

-0.08

 maze

-0.08

POSITIVE LOGITS

job

0.16

 roof

0.14

job

0.14

 stable

0.13

Job

0.13

 life

0.13

 career

0.13

JOB

0.13

 sense

0.12

Job

0.12

Activations Density 0.104%