INDEX
Explanations
terms related to sexual and reproductive health and rights
New Auto-Interp
Negative Logits
emer
-0.16
aret
-0.15
cep
-0.15
arent
-0.15
DISP
-0.15
جÙĪ
-0.14
nown
-0.14
jej
-0.14
igon
-0.14
avou
-0.14
POSITIVE LOGITS
ized
0.35
ised
0.28
ization
0.26
IZED
0.26
izing
0.26
izes
0.24
izable
0.24
izers
0.23
izer
0.22
izations
0.21
Activations Density 0.015%