INDEX
Explanations
text related to various religions and religious practices
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.20
1.2%
1053
+0.09
0.6%
314
+0.09
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1777
+0.20
0.02
314
+0.09
0.02
1202
+0.09
0.01
Negative Logits
<bos>
-3.42
ⓧ
-0.84
/**
-0.84
<?
-0.81
/*
-0.72
<tfoot>
-0.70
-0.68
HasAnnotation
-0.65
itemize
-0.65
Халык
-0.65
POSITIVE LOGITS
Juf
1.61
bandung
1.55
Minang
1.49
reluct
1.46
Momb
1.44
Augu
1.44
unlaw
1.42
véhic
1.42
Février
1.39
milano
1.39
Activations Density 0.056%