INDEX
Explanations
mentions of relationships and emotional attributes in obituaries
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.07
0.3%
984
+0.06
0.2%
605
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
570
+0.07
0.02
984
+0.06
0.02
1495
+0.06
0.02
Negative Logits
<bos>
-0.97
-0.74
<?
-0.71
/***
-0.67
})();
-0.65
ⓧ
-0.62
lateinit
-0.62
public
-0.61
ValueGenerated
-0.61
RouterModule
-0.60
POSITIVE LOGITS
loving
1.86
Loving
1.62
Loving
1.44
loving
1.30
meis
1.18
stockholm
1.16
foon
1.16
vns
1.13
ftre
1.12
thut
1.11
Activations Density 0.107%