INDEX
Explanations
Spanish surnames that contain a common pattern of vowels and consonants
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
689
+0.13
0.6%
573
+0.12
0.5%
239
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.13
0.11
1614
+0.12
0.09
227
+0.11
0.09
Negative Logits
<bos>
-0.78
<?
-0.63
/**
-0.59
<?
-0.59
-0.56
wretch
-0.55
lemmas
-0.54
wasn
-0.54
INVOLVED
-0.53
epistle
-0.52
POSITIVE LOGITS
nece
1.22
sopr
1.14
sappi
1.07
dispen
1.05
immen
1.05
apparti
1.05
ridu
1.05
divertimento
1.04
soggior
1.04
tramont
1.03
Activations Density 1.060%