INDEX

Explanations

health risks and accidents

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

ccak

-0.09

alah

-0.09

layers

-0.09

 Decay

-0.09

 saliva

-0.09

 fluores

-0.09

 Einsatz

-0.08

ancell

-0.08

 Clover

-0.08

ura

-0.08

POSITIVE LOGITS

 explosion

0.14

 exposure

0.13

fl

0.13

eye

0.13

 Explosion

0.12

çĪĨ

0.12

 skin

0.12

 potential

0.12

 explosions

0.12

Eye

0.12

Activations Density 0.029%