INDEX
Explanations
phrases related to living spaces and accommodations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.10
0.5%
866
+0.06
0.3%
1137
+0.06
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
102
+0.10
0.05
866
+0.06
0.04
1887
+0.06
0.04
Negative Logits
<bos>
-1.65
/**
-0.84
-0.80
/*
-0.80
/***
-0.80
<?
-0.74
public
-0.72
{{---0.72
///**
-0.71
also
-0.70
POSITIVE LOGITS
Juf
2.13
increa
2.13
affor
2.13
maneu
2.06
accla
2.04
impra
2.04
wherea
2.01
fta
1.99
stockholm
1.98
ftu
1.93
Activations Density 0.094%