INDEX
Explanations
concepts related to individual rights and authority in healthcare and reproductive matters
New Auto-Interp
Negative Logits
weis
-0.20
iesel
-0.15
orus
-0.15
luž
-0.14
ogle
-0.14
ören
-0.14
aise
-0.14
ouched
-0.14
zan
-0.13
iais
-0.13
POSITIVE LOGITS
right
0.73
RIGHT
0.56
right
0.56
Right
0.54
Right
0.50
-right
0.48
.right
0.46
_right
0.44
пÑĢаво
0.44
right
0.43
Activations Density 0.182%