INDEX
Explanations
transportation-related terms, especially about commuting and cultural aspects related to transportation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
964
+0.17
0.5%
198
+0.15
0.4%
1533
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
198
+0.17
0.05
964
+0.15
0.04
1533
+0.12
0.01
Negative Logits
logis
-0.93
lele
-0.92
kano
-0.90
kram
-0.90
kac
-0.87
dises
-0.86
kapa
-0.86
kasa
-0.86
apparti
-0.85
kaka
-0.83
POSITIVE LOGITS
culture
0.73
culture
0.58
Culture
0.57
cultural
0.56
tradition
0.54
MediatR
0.54
culturally
0.54
Culture
0.53
traditionally
0.53
cultures
0.52
Activations Density 0.592%