INDEX
Explanations
mentions of vendors or sponsorships
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
687
+0.17
0.9%
303
+0.14
0.8%
1806
+0.14
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
889
+0.17
0.03
1896
+0.14
0.02
395
+0.14
0.03
Negative Logits
<bos>
-1.08
OGND
-0.82
Asimismo
-0.69
InputBorder
-0.65
Conclusiones
-0.63
Conclusión
-0.63
netinet
-0.63
SystemColors
-0.62
cur
-0.62
CONCLUSIONES
-0.60
POSITIVE LOGITS
increa
1.28
emphat
1.24
shenan
1.23
affor
1.21
unspeak
1.20
attemp
1.20
horrend
1.19
tolerably
1.16
seoul
1.16
reluct
1.15
Activations Density 0.502%