INDEX
Explanations
transportation-related terms and concepts, especially related to biking and public transportation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
964
+0.11
0.3%
1601
+0.10
0.3%
1013
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1601
+0.11
0.04
942
+0.10
0.04
939
+0.10
0.04
Negative Logits
distru
-0.71
accla
-0.70
abbra
-0.65
parlar
-0.65
fatis
-0.63
disgra
-0.63
pessi
-0.63
ritard
-0.62
viciss
-0.62
applau
-0.61
POSITIVE LOGITS
commute
0.64
<bos>
0.64
transportation
0.63
commuting
0.63
mobility
0.61
pedestrians
0.60
pedestrian
0.56
convenience
0.56
transport
0.54
amenities
0.53
Activations Density 0.321%