INDEX
Explanations
information related to political leaders and policy making
references to the election and presidency of Donald Trump
New Auto-Interp
Head Attr Weights
0:0.07
1:0.05
2:0.08
3:0.08
4:0.12
5:0.10
6:0.03
7:0.04
8:0.11
9:0.14
10:0.09
11:0.03
Negative Logits
epid
-1.39
erb
-1.33
knit
-1.27
iotic
-1.26
ivable
-1.25
atable
-1.24
pload
-1.24
osures
-1.19
itamin
-1.19
γ
-1.18
POSITIVE LOGITS
aign
1.37
clinton
1.35
�士
1.34
riel
1.33
appoint
1.31
ascus
1.29
thous
1.26
��
1.24
pard
1.21
Hillary
1.20
Activations Density 0.007%