INDEX
Explanations
mentions of the location "San Diego."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.07
0.2%
1052
+0.07
0.2%
1708
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1102
+0.07
0.03
1898
+0.07
0.03
1429
+0.06
0.03
Negative Logits
<bos>
-1.12
/**
-0.84
<?
-0.80
ⓧ
-0.70
-0.64
/*
-0.64
reap
-0.62
pick
-0.60
try
-0.60
hold
-0.60
POSITIVE LOGITS
Diego
1.77
wien
1.67
Diego
1.61
DIEGO
1.58
ftu
1.56
diego
1.56
vns
1.54
bordeaux
1.53
provence
1.52
fta
1.52
Activations Density 0.164%