INDEX

Explanations

You can use

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

 Optionally

-0.11

 optionally

-0.09

RIES

-0.09

loggedin

-0.09

 ï¾Ĭ

-0.08

.qt

-0.08

ï½²

-0.08

illet

-0.08

wig

-0.08

mer

-0.08

POSITIVE LOGITS

åħ¸

0.12

ä¾ĭå¦Ĥ

0.12

 example

0.11

 typically

0.11

 Again

0.11

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.11

ury

0.10

Gig

0.10

 something

0.10

.Skip

0.10

Activations Density 0.060%