INDEX
Explanations
information related to statistics and data analysis
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1967
+0.33
1.2%
1343
+0.23
0.8%
674
+0.19
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1967
+0.33
0.05
1804
+0.23
0.06
2011
+0.19
0.04
Negative Logits
,
-0.84
that
-0.79
a
-0.78
.
-0.77
and
-0.75
for
-0.75
or
-0.74
so
-0.74
which
-0.74
as
-0.73
POSITIVE LOGITS
Ottobre
1.79
utop
1.73
incess
1.71
alkoh
1.68
Giugno
1.63
marte
1.63
Settembre
1.62
solidar
1.61
ordina
1.61
Luglio
1.60
Activations Density 0.240%