INDEX

Explanations

relationship status and feelings

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

 honeymoon

-0.12

å¤«

-0.12

 Couples

-0.12

 couples

-0.12

 husbands

-0.10

loff

-0.10

 wife

-0.09

married

-0.09

_UNIX

-0.09

orge

-0.09

POSITIVE LOGITS

 serial

0.16

 single

0.15

serial

0.14

 dating

0.14

 Single

0.14

 SINGLE

0.14

Single

0.14

 dated

0.14

 independence

0.14

single

0.13

Activations Density 0.100%