INDEX
Explanations
adjectives related to softness or tenderness
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.12
0.6%
1575
+0.10
0.5%
1265
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1575
+0.12
0.04
1385
+0.10
0.04
147
+0.10
0.02
Negative Logits
<bos>
-2.14
Bibliograf
-0.73
glMatrixMode
-0.72
ⓧ
-0.70
<?
-0.68
/*
-0.65
-0.65
/**
-0.61
nawr
-0.59
glPushMatrix
-0.57
POSITIVE LOGITS
jaya
1.22
maroc
1.18
riva
1.16
fordable
1.15
stockholm
1.14
frankfurt
1.14
bangkok
1.12
GENTLE
1.12
Minang
1.11
beverly
1.09
Activations Density 0.250%