INDEX

Explanations

stand up for yourself

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

ajo

-0.10

 ours

-0.10

 Hawkins

-0.09

ÐµÑİ

-0.09

 hawk

-0.08

ACE

-0.08

 lance

-0.08

 Nolan

-0.08

orde

-0.08

.IsNull

-0.08

POSITIVE LOGITS

 self

0.41

 Self

0.35

èĩªå·±

0.31

 ÑģÐµÐ±Ñı

0.31

 SELF

0.31

èĩª

0.30

 ÑģÐµÐ±Ðµ

0.30

Self

0.29

self

0.29

 Selbst

0.29

Activations Density 0.217%