INDEX
Explanations
family relationships and personal details like names and locations of individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.26
1.1%
1343
+0.12
0.5%
776
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
776
+0.26
0.10
1910
+0.12
0.06
1978
+0.09
0.07
Negative Logits
<bos>
-2.82
ⓧ
-0.98
-0.81
Autoritní
-0.77
ValueGenerated
-0.74
rawDesc
-0.72
/**
-0.68
/*++
-0.67
FunctionFlags
-0.66
zydent
-0.63
POSITIVE LOGITS
maroc
1.23
napoli
1.18
meis
1.14
marseille
1.10
hcm
1.10
mef
1.10
Jambi
1.08
aen
1.07
tramont
1.05
wien
1.05
Activations Density 0.587%