INDEX
Explanations
postal addresses and related information such as phone numbers and bank details
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.22
0.8%
1343
+0.11
0.4%
1741
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1692
+0.22
0.02
1343
+0.11
0.03
139
+0.08
0.03
Negative Logits
<bos>
-1.31
///**
-0.93
/***
-0.92
<?
-0.83
//};
-0.79
/*!
-0.74
//*/
-0.70
/**
-0.70
//});
-0.64
<>
-0.62
POSITIVE LOGITS
bangkok
0.91
unden
0.91
stockholm
0.89
kyo
0.88
tokyo
0.87
blackpink
0.86
seoul
0.86
amsterdam
0.84
brooklyn
0.84
effe
0.84
Activations Density 0.054%