INDEX
Explanations
verbs indicating action or movement
New Auto-Interp
Head Attr Weights
0:0.08
1:0.08
2:0.07
3:0.08
4:0.08
5:0.08
6:0.07
7:0.08
8:0.07
9:0.08
10:0.09
11:0.07
Negative Logits
jur
-2.38
manoeuv
-2.01
Vulkan
-2.00
releg
-1.98
neb
-1.95
gloss
-1.93
acron
-1.91
decl
-1.91
pires
-1.87
prevail
-1.84
POSITIVE LOGITS
aky
2.41
ucket
2.34
plet
2.33
aditional
2.27
akable
2.26
orted
2.26
uben
2.25
atts
2.24
ijah
2.19
hoe
2.19
Activations Density 0.000%