INDEX
Explanations
phrases related to scientific equations and theories
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.28
0.9%
2015
+0.18
0.6%
1499
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1499
+0.28
0.04
876
+0.18
-0.00
872
+0.15
0.04
Negative Logits
Juventud
-0.82
Congreg
-0.77
Immig
-0.74
Caritas
-0.72
democra
-0.70
fiestas
-0.68
Nonprofit
-0.65
Salón
-0.65
Fuerzas
-0.64
Noche
-0.62
POSITIVE LOGITS
embodi
1.05
waer
1.04
Février
1.03
jacques
1.01
vété
0.98
chèvre
0.97
pandan
0.97
veau
0.97
alberto
0.95
automne
0.95
Activations Density 0.221%