INDEX
Explanations
references to political ideologies and movements, especially those related to fundamentalism and liberalism
New Auto-Interp
Negative Logits
usta
-0.15
ãģķãĤĵãģ¯
-0.15
aths
-0.14
azen
-0.14
ieten
-0.14
æĪIJç«ĭ
-0.14
žel
-0.14
vida
-0.14
ifact
-0.14
athi
-0.14
POSITIVE LOGITS
ism
0.15
/bower
0.14
Christine
0.14
Sized
0.14
Rack
0.14
.Values
0.14
Streamer
0.13
Kong
0.13
Latch
0.13
levard
0.13
Activations Density 0.226%