INDEX
Explanations
references to curing diseases or ailments
New Auto-Interp
Negative Logits
en
-0.54
inde
-0.49
fede
-0.48
reng
-0.48
zed
-0.47
穿
-0.47
met
-0.47
i
-0.46
ester
-0.46
пер
-0.46
POSITIVE LOGITS
Савезне
1.07
resourceCulture
0.93
GEBURTSDATUM
0.93
KURZBESCHREIBUNG
0.90
AsUp
0.86
twimg
0.85
protoimpl
0.84
rrggbb
0.83
FXMLLoader
0.82
gynhyrchwyd
0.81
Activations Density 0.072%