INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.2%
889
+0.05
0.2%
1839
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
0
-0.93
5
-0.93
3
-0.92
2
-0.92
7
-0.91
6
-0.90
8
-0.89
4
-0.88
1
-0.87
9
-0.83
POSITIVE LOGITS
<bos>
9.45
intersper
1.66
Autoritní
1.64
GEBURTSDATUM
1.62
ⓧ
1.61
expandindo
1.59
encomp
1.58
sappi
1.55
<?
1.50
dovr
1.48
Activations Density 0.000%
No Known Activations
This feature has no known activations.