INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.22
0.7%
1306
+0.06
0.2%
866
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.22
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
in
-1.07
,
-0.99
no
-0.99
to
-0.97
a
-0.97
an
-0.97
far
-0.96
as
-0.96
for
-0.94
all
-0.93
POSITIVE LOGITS
<bos>
7.25
parteci
1.96
Ottobre
1.93
ftu
1.89
fign
1.88
Luglio
1.87
autunno
1.82
Settembre
1.82
»>
1.80
dispen
1.79
Activations Density 0.000%
No Known Activations
This feature has no known activations.