INDEX
Explanations
words related to gambling or competitive games
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
871
+0.14
0.8%
481
+0.14
0.8%
544
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.14
0.09
227
+0.14
0.09
871
+0.14
0.05
Negative Logits
<bos>
-1.80
ngayon
-0.70
namin
-0.70
tayo
-0.69
natin
-0.66
AssemblyCompany
-0.65
kasama
-0.64
katapos
-0.62
/*
-0.62
hanggang
-0.60
POSITIVE LOGITS
quoique
1.07
aussitôt
1.01
stockholm
1.00
jorge
1.00
Nug
0.95
Augu
0.95
sergio
0.94
santiago
0.93
Teg
0.93
quelquefois
0.91
Activations Density 0.996%