INDEX
Explanations
numeric values indicating a result or outcome
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.11
0.4%
528
+0.05
0.2%
629
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1076
+0.11
0.03
985
+0.05
0.03
921
+0.04
0.03
Negative Logits
<bos>
-1.59
<!--
-0.66
//@
-0.63
ੇ
-0.59
onBind
-0.58
<tfoot>
-0.57
/**
-0.57
<!--<
-0.57
/*
-0.57
///**
-0.55
POSITIVE LOGITS
maneu
1.95
affor
1.66
accla
1.62
increa
1.60
disagre
1.59
shenan
1.58
gaily
1.55
lidl
1.53
impra
1.52
reluct
1.51
Activations Density 0.098%