INDEX
Explanations
incidents involving animals or wildlife
New Auto-Interp
Negative Logits
amu
-0.17
voksen
-0.16
eldorf
-0.16
bourg
-0.15
nds
-0.15
sts
-0.15
Typed
-0.14
chsel
-0.14
wireType
-0.14
reste
-0.14
POSITIVE LOGITS
iece
0.18
каÑģ
0.15
Boss
0.15
dej
0.14
saw
0.14
712
0.14
olas
0.14
jsx
0.13
ëĤľ
0.13
PAD
0.13
Activations Density 0.020%