INDEX
Explanations
occurrences of movement-related terms, including actions involving physical movement and mobility restrictions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
690
+0.11
0.3%
906
+0.11
0.3%
1819
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.11
0.07
1819
+0.11
0.07
690
+0.11
0.03
Negative Logits
Febru
-0.97
lancia
-0.95
Cfr
-0.95
simplif
-0.93
tramont
-0.93
Keny
-0.93
embra
-0.93
Chá
-0.93
Olimpia
-0.92
Juf
-0.91
POSITIVE LOGITS
movements
1.02
movement
1.01
motion
0.84
motions
0.81
movements
0.79
movement
0.78
moves
0.77
Movement
0.76
move
0.70
moving
0.69
Activations Density 0.544%