INDEX

Explanations

Ð¿Ð¾Ð»ÑĥÑ with Ð¿Ð¾Ð¿

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

Negative Logits

 Ð·Ð°Ð²Ð¸ÑģÐ¸Ð¼

-0.11

ancel

-0.10

ÑģÐ¸Ð»ÑĮ

-0.10

åĽº

-0.09

-cli

-0.09

 elig

-0.09

 Ð¸Ð¼Ñĥ

-0.09

ponsive

-0.09

 Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´Ñĥ

-0.09

 prostitu

-0.09

POSITIVE LOGITS

Bol

0.13

âĦĸâĦĸ

0.12

ÐĲÑĢÑħÑĸÐ²

0.11

 fate

0.10

 actively

0.10

plen

0.10

 Â«

0.10

è¶£

0.10

@mail

0.10

 descent

0.10

Activations Density 0.213%

No Known Activations