INDEX

Explanations

favor, favorable, favorites

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

ed

-0.12

acci

-0.10

ears

-0.10

es

-0.10

eph

-0.10

eln

-0.09

ically

-0.09

zos

-0.09

ertainment

-0.09

POSITIVE LOGITS

ably

0.27

ited

0.16

ing

0.16

ously

0.14

favor

0.12

abilia

0.12

 Favor

0.12

iten

0.12

rous

0.12

 favor

0.12

Activations Density 0.021%