INDEX
Explanations
references to financial status and familial background
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
509
+0.11
0.3%
674
+0.10
0.3%
1533
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
509
+0.11
0.06
1260
+0.10
0.01
1533
+0.10
0.02
Negative Logits
wien
-1.80
increa
-1.78
unden
-1.77
inev
-1.73
maneu
-1.71
affor
-1.70
wherea
-1.69
„,
-1.68
mef
-1.68
impra
-1.67
POSITIVE LOGITS
<bos>
0.96
AssemblyCompany
0.74
ParallelGroup
0.71
GraphicsUnit
0.67
dad
0.66
RTDA
0.66
xase
0.65
father
0.63
setViewName
0.62
父
0.61
Activations Density 0.430%