INDEX
Explanations
references to personal empowerment and individual rights, particularly related to reproductive freedom and health
New Auto-Interp
Negative Logits
357
-0.15
aises
-0.15
eldon
-0.15
SCO
-0.15
ahir
-0.14
Touches
-0.14
ahr
-0.14
subscriber
-0.14
loser
-0.14
riel
-0.13
POSITIVE LOGITS
0.15
individual
0.15
OWN
0.15
own
0.15
CHO
0.14
0.14
LI
0.14
огÑĢа
0.14
SELF
0.14
li
0.14
Activations Density 0.209%