INDEX
Explanations
details related to the city of Montreal
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
31
+0.15
0.6%
1387
+0.14
0.5%
645
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1335
+0.15
0.03
1387
+0.14
0.02
227
+0.13
0.02
Negative Logits
Sén
-0.98
Messieurs
-0.95
Meille
-0.91
Lettre
-0.90
toul
-0.87
Venise
-0.87
Docteur
-0.86
chante
-0.85
Châ
-0.85
chevalier
-0.83
POSITIVE LOGITS
Montreal
1.31
Montreal
1.15
Quebec
1.12
canadian
1.03
excru
1.03
moun
1.01
jurassic
1.00
increa
0.97
thut
0.95
fuf
0.94
Activations Density 0.074%