INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.23
0.7%
1626
+0.04
0.1%
335
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.23
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
unlaw
-2.05
reluct
-2.00
disgra
-1.94
stockholm
-1.94
impractica
-1.91
sputnik
-1.85
wien
-1.85
increa
-1.84
inev
-1.83
impra
-1.81
POSITIVE LOGITS
<bos>
8.68
GEBURTSDATUM
1.70
expandindo
1.55
betweenstory
1.45
Jeografia
1.31
principalColumn
1.31
Panamoan
1.30
Paglinawan
1.28
Geplaatst
1.26
'\\;'
1.25
Activations Density 0.000%
No Known Activations
This feature has no known activations.