INDEX
Explanations
names of people and references to personal relationships or events involving those people being accused or convicted of various actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.39
1.3%
184
+0.23
0.8%
1967
+0.20
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1842
+0.39
0.06
227
+0.23
0.06
856
+0.20
0.03
Negative Logits
nélk
-0.50
physiologic
-0.45
createdDate
-0.44
mę
-0.44
chłop
-0.43
ddelweddau
-0.42
infographics
-0.42
resear
-0.41
bł
-0.41
experiential
-0.41
POSITIVE LOGITS
CiNii
0.82
quoique
0.81
Février
0.81
Giugno
0.81
Décembre
0.80
Cfr
0.78
charité
0.78
Portail
0.77
exé
0.77
nomme
0.76
Activations Density 0.261%