INDEX
Explanations
information related to criminal activities and police investigations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.19
0.7%
1013
+0.11
0.4%
856
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1855
+0.19
0.07
1288
+0.11
0.08
856
+0.09
0.06
Negative Logits
<bos>
-2.73
ⓧ
-0.85
/***
-0.77
/**
-0.68
<!--
-0.66
<?
-0.64
/*!
-0.62
},{
-0.62
-0.61
бият
-0.60
POSITIVE LOGITS
maneu
1.57
Minang
1.38
reluct
1.29
Juf
1.29
impractica
1.26
unwarran
1.21
disagre
1.20
ftu
1.18
excru
1.18
inev
1.16
Activations Density 0.507%