INDEX
Explanations
items related to legal or governmental institutions
New Auto-Interp
Head Attr Weights
0:0.02
1:0.01
2:0.06
3:0.06
4:0.05
5:0.03
6:0.36
7:0.04
8:0.03
9:0.04
10:0.10
11:0.14
Negative Logits
itious
-1.63
iled
-1.42
abase
-1.41
orable
-1.39
isner
-1.32
clusively
-1.28
uria
-1.28
istered
-1.25
arth
-1.25
gent
-1.23
POSITIVE LOGITS
fell
1.58
�
1.49
士
1.34
RG
1.21
ⓘ
1.21
essen
1.21
wear
1.21
�
1.20
addons
1.20
shoot
1.18
Activations Density 0.000%