INDEX
Explanations
mentions of the word "mall" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
411
+0.15
0.6%
67
+0.13
0.5%
1331
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
411
+0.15
0.02
1480
+0.13
0.02
1331
+0.12
0.02
Negative Logits
affor
-0.99
increa
-0.99
?...
-0.96
encomp
-0.95
intersper
-0.93
!...
-0.92
jacques
-0.91
amsterdam
-0.90
eiffel
-0.90
basque
-0.88
POSITIVE LOGITS
mall
1.55
Mall
1.47
Mall
1.32
malls
1.28
mall
1.27
MALL
1.03
shopping
0.81
Shopping
0.71
shopping
0.70
Shopping
0.64
Activations Density 0.070%