INDEX
Explanations
references to infidelity and affairs in relationships
New Auto-Interp
Negative Logits
edic
-0.15
اÙĦب
-0.15
utters
-0.15
radient
-0.14
iri
-0.14
boro
-0.14
हल
-0.14
664
-0.14
utable
-0.14
Mocks
-0.14
POSITIVE LOGITS
soil
0.16
Reyes
0.15
angu
0.15
нÑĥ
0.15
åľ¨çº¿è§Ĥçľĭ
0.15
itler
0.14
ored
0.14
imli
0.14
addy
0.14
uchs
0.14
Activations Density 0.045%