INDEX
Explanations
detailed descriptions or assessments
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1804
+0.10
0.3%
872
+0.09
0.2%
569
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
249
+0.10
0.06
1287
+0.09
0.04
919
+0.08
0.03
Negative Logits
kram
-1.43
alkoh
-1.36
plak
-1.27
„,
-1.27
solidar
-1.26
meis
-1.25
makro
-1.25
stoff
-1.22
gesta
-1.22
ohr
-1.20
POSITIVE LOGITS
of
1.22
của
0.91
of
0.88
Of
0.85
Of
0.82
ของ
0.82
thereof
0.74
της
0.64
של
0.62
ของ
0.61
Activations Density 0.322%