INDEX
Explanations
words related to financial transactions and scams
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2015
+0.09
0.3%
198
+0.08
0.2%
1978
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2015
+0.09
0.03
1385
+0.08
0.07
1013
+0.07
0.07
Negative Logits
certainly
-0.68
Thông
-0.64
also
-0.64
ਿ
-0.63
could
-0.63
public
-0.62
ਿੱ
-0.62
perhaps
-0.62
ਹ
-0.62
adomo
-0.62
POSITIVE LOGITS
ecru
2.01
swarovski
1.96
ftre
1.94
maneu
1.89
ftu
1.87
fta
1.80
thut
1.72
Khart
1.71
reft
1.70
affor
1.70
Activations Density 0.925%