INDEX
Explanations
words that end with the suffix 'ym'
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
111
+0.10
0.6%
410
+0.10
0.6%
376
+0.09
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
13
+0.10
0.01
4
+0.10
0.01
108
+0.09
0.01
Negative Logits
latter
-1.63
suspected
-1.52
iver
-1.51
hip
-1.50
stomach
-1.50
conceal
-1.48
xture
-1.42
mind
-1.41
omen
-1.39
expect
-1.37
POSITIVE LOGITS
ĻĤ
2.28
posium
2.19
fony
2.09
ÅĽci
1.96
Awards
1.83
enos
1.77
kur
1.76
İ
1.75
orphous
1.63
eno
1.61
Activations Density 0.574%