INDEX
Explanations
references to military training and operations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.33
1.4%
394
+0.14
0.6%
1842
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.33
0.17
1499
+0.14
0.08
453
+0.11
0.07
Negative Logits
<bos>
-1.92
lateinit
-0.66
Попис
-0.65
<?
-0.64
/*
-0.60
setDo
-0.60
intios
-0.60
таратура
-0.57
السكان
-0.57
ⓧ
-0.57
POSITIVE LOGITS
Minang
1.83
Khart
1.57
Juf
1.51
Banjar
1.49
Keny
1.48
Pekan
1.48
Karang
1.42
saar
1.42
Palembang
1.41
Muhamma
1.39
Activations Density 5.631%