INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.36
1.7%
1741
+0.06
0.3%
1445
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.36
0.00
0
-0.06
0.00
1
-0.04
0.00
Negative Logits
-1.31
0
-1.29
1
-1.28
3
-1.26
.
-1.26
2
-1.26
5
-1.25
6
-1.24
4
-1.24
7
-1.24
POSITIVE LOGITS
<bos>
11.62
expandindo
2.50
GEBURTSDATUM
2.41
betweenstory
2.22
Autoritní
2.12
ⓧ
2.11
'\\;'
2.01
Administrativna
1.99
kasarigan
1.98
Italijani
1.92
Activations Density 0.000%
No Known Activations
This feature has no known activations.