INDEX
Explanations
names related to the name "Rosa"
proper nouns related to individuals or entities
New Auto-Interp
Negative Logits
rics
-0.80
ature
-0.79
ship
-0.77
erous
-0.73
ridges
-0.71
ships
-0.70
eer
-0.70
piece
-0.69
sw
-0.69
entric
-0.68
POSITIVE LOGITS
Luxem
1.17
xual
0.93
osa
0.90
ctive
0.76
itor
0.74
Osw
0.72
soup
0.72
hea
0.70
velt
0.69
ient
0.69
Activations Density 0.080%