INDEX
Explanations
words related to a specific location, specifically the downtown area of a city
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.07
0.3%
1034
+0.07
0.2%
161
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1485
+0.07
0.03
1013
+0.07
0.03
579
+0.07
0.02
Negative Logits
ⓧ
-0.91
-0.89
/*
-0.87
/**
-0.86
<?
-0.81
/*++
-0.74
<?
-0.71
#
-0.70
enable
-0.68
//{
-0.68
POSITIVE LOGITS
downtown
2.05
Downtown
1.99
downtown
1.98
Downtown
1.97
aen
1.78
maneu
1.66
fup
1.65
impra
1.65
inev
1.64
levis
1.64
Activations Density 0.117%