INDEX

Explanations

contact followed by information or us

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

 scal

-0.09

onda

-0.09

utter

-0.09

seo

-0.09

CHAT

-0.09

auc

-0.09

ALSE

-0.09

IDL

-0.09

ule

-0.08

ÑĴ

-0.08

POSITIVE LOGITS

ually

0.22

 lenses

0.19

ez

0.17

 lens

0.17

ors

0.17

ees

0.17

ual

0.16

anos

0.15

less

0.15

Us

0.13

Activations Density 0.017%