INDEX
Explanations
mentions of the name "Leon."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1137
+0.14
0.8%
489
+0.14
0.8%
812
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1097
+0.14
0.03
1575
+0.14
0.02
227
+0.13
0.02
Negative Logits
<bos>
-1.38
aukš
-0.56
<?
-0.49
way
-0.47
/**
-0.47
tube
-0.46
/*
-0.45
vandens
-0.45
biztons
-0.45
gazed
-0.45
POSITIVE LOGITS
Leon
1.62
Leon
1.48
leon
1.43
LEON
1.35
LEON
1.32
Léon
1.16
Leonard
1.15
leon
1.13
Leonard
1.05
León
1.05
Activations Density 0.121%