INDEX
Explanations
data related to social issues and statistics on various topics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.11
0.3%
1415
+0.08
0.2%
143
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
619
+0.11
0.03
111
+0.08
0.02
143
+0.07
0.03
Negative Logits
depic
-0.98
pamph
-0.96
intersper
-0.92
emphat
-0.85
fto
-0.84
accla
-0.83
„,
-0.80
practition
-0.78
passim
-0.77
indestru
-0.77
POSITIVE LOGITS
majority
0.69
percent
0.68
account
0.62
accounting
0.62
part
0.60
accounted
0.60
%
0.60
half
0.60
percent
0.59
percentage
0.58
Activations Density 0.175%