INDEX
Explanations
references to territorial behavior or ownership
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1810
+0.14
0.7%
966
+0.14
0.7%
1178
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
437
+0.14
0.03
1438
+0.14
0.02
239
+0.12
0.02
Negative Logits
<bos>
-2.20
-0.69
<?
-0.62
initComponents
-0.58
clinch
-0.57
inject
-0.57
Jîn
-0.55
/**
-0.55
πάρχ
-0.55
/*
-0.54
POSITIVE LOGITS
territory
1.39
territory
1.33
Territory
1.30
oleo
1.24
bordeaux
1.23
parma
1.17
swarovski
1.15
cabrio
1.14
levis
1.13
Territory
1.13
Activations Density 0.222%