INDEX

Explanations

create own

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

Negative Logits

ufs

-0.10

igo

-0.09

aus

-0.09

.Singleton

-0.09

çļĦæīĭ

-0.09

-0.08

oken

-0.08

OOD

-0.08

globals

-0.08

POSITIVE LOGITS

own

0.56

èĩªå·±çļĦ

0.55

 eigenen

0.40

 prÃ³p

0.39

own

0.38

 propia

0.38

Own

0.37

 vlastnÃŃ

0.37

 kendi

0.36

 ÑģÐ¾Ð±ÑģÑĤÐ²ÐµÐ½

0.34

Activations Density 0.146%

No Known Activations