INDEX
Explanations
mentions of shopping malls
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.21
0.8%
1013
+0.13
0.5%
203
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1013
+0.21
0.08
964
+0.13
0.06
203
+0.10
0.05
Negative Logits
<bos>
-2.18
intersper
-1.19
encomp
-1.11
-1.00
ⓧ
-0.98
<?
-0.96
<?
-0.96
whistled
-0.88
disbur
-0.88
/***
-0.86
POSITIVE LOGITS
mall
0.84
Mall
0.84
Mall
0.74
shopping
0.73
Shopping
0.72
catég
0.70
Shopping
0.66
mall
0.64
malls
0.63
officiels
0.57
Activations Density 0.474%