INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.32
1.3%
1045
+0.06
0.2%
1741
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.32
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
in
-1.01
that
-0.99
to
-0.98
not
-0.98
,
-0.97
for
-0.96
also
-0.95
as
-0.95
so
-0.93
he
-0.93
POSITIVE LOGITS
<bos>
9.96
GEBURTSDATUM
2.15
parteci
2.14
dispen
2.08
autunno
2.04
fatis
2.01
ftu
1.98
sappi
1.93
paff
1.91
dises
1.90
Activations Density 0.000%
No Known Activations
This feature has no known activations.