INDEX
Explanations
terms related to people, relationships, and interactions between individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1103
+0.21
1.1%
757
+0.14
0.7%
1035
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1103
+0.21
0.03
1035
+0.14
0.02
1137
+0.12
0.02
Negative Logits
<bos>
-1.63
intersper
-0.77
<?
-0.75
ⓧ
-0.72
encomp
-0.65
underval
-0.63
дописавши
-0.62
superintend
-0.62
apprehen
-0.60
recollect
-0.60
POSITIVE LOGITS
Whom
1.14
whom
1.07
whom
1.06
Whom
0.98
Luglio
0.93
Ottobre
0.85
borsa
0.83
Giugno
0.78
GYPT
0.75
ristor
0.75
Activations Density 0.259%