INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.32
1.3%
1741
+0.06
0.3%
1120
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.32
0.00
0
-0.06
0.00
1
-0.06
0.00
Negative Logits
to
-1.34
.
-1.14
,
-1.10
in
-1.08
so
-1.08
-1.07
as
-1.04
for
-1.04
and
-1.04
do
-1.03
POSITIVE LOGITS
<bos>
10.68
GEBURTSDATUM
2.16
ftu
2.08
expandindo
2.04
kasarigan
2.00
ftre
1.95
fatis
1.95
dovr
1.92
Autoritní
1.91
paff
1.90
Activations Density 0.000%
No Known Activations
This feature has no known activations.