INDEX
Explanations
mentions of criminal activities and legal proceedings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.2%
856
+0.22
0.8%
184
+0.20
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1804
+0.31
0.01
856
+0.22
0.01
599
+0.20
0.01
Negative Logits
emphat
-1.23
impra
-1.22
maneu
-1.17
increa
-1.16
indestru
-1.10
affor
-1.08
embodi
-1.07
disagre
-1.05
inev
-1.05
uninten
-0.98
POSITIVE LOGITS
<bos>
1.21
BeginInit
0.75
bewerken
0.73
titleMargin
0.71
rungsseite
0.68
estekak
0.67
jsxFileName
0.66
IVEREF
0.65
Jeografia
0.63
RTGC
0.63
Activations Density 0.015%