INDEX
Explanations
references to supernatural creatures, specifically werewolves, vampires, and related themes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.20
0.8%
1842
+0.13
0.5%
394
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1842
+0.20
0.03
1399
+0.13
0.04
1597
+0.09
0.03
Negative Logits
<bos>
-3.26
AssemblyCompany
-0.91
SequentialGroup
-0.77
/***
-0.75
AndroidJUnit
-0.70
public
-0.69
AssemblyProduct
-0.68
Enllaços
-0.66
private
-0.65
ніципа
-0.65
POSITIVE LOGITS
unlaw
1.76
sovere
1.72
unwarran
1.72
disagre
1.66
Juf
1.65
inev
1.64
emphat
1.63
impractica
1.63
increa
1.61
reluct
1.60
Activations Density 0.622%