INDEX

Explanations

quirky descriptions

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

Dia

-0.09

áº£nh

-0.09

.scalablytyped

-0.09

nock

-0.09

 whit

-0.09

ULE

-0.08

eci

-0.08

igroup

-0.08

 humanoid

-0.08

POSITIVE LOGITS

 instead

0.10

ieber

0.09

rne

0.09

 edition

0.09

 Genius

0.09

enc

0.09

ogo

0.09

 Ð²Ð¼ÐµÑģÑĤ

0.08

instead

0.08

åİ»äºĨ

0.08

Activations Density 0.176%