INDEX
Explanations
conjunctions and other linking words that describe relationships between ideas or entities
New Auto-Interp
Head Attr Weights
0:0.03
1:0.01
2:0.06
3:0.05
4:0.06
5:0.03
6:0.41
7:0.05
8:0.04
9:0.05
10:0.10
11:0.06
Negative Logits
ivan
-1.23
BILITY
-1.22
pole
-1.21
nen
-1.21
Cheong
-1.11
��
-1.10
princ
-1.10
erection
-1.08
hastily
-1.08
spons
-1.04
POSITIVE LOGITS
Gujar
1.29
Confederation
1.28
bia
1.24
cult
1.23
将
1.20
ilic
1.19
Warcraft
1.18
Terrorism
1.18
姫
1.17
iferation
1.16
Activations Density 0.003%