INDEX
Explanations
information about a person's professional background and affiliations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.16
0.5%
198
+0.10
0.3%
1870
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.16
0.08
1980
+0.10
0.03
1694
+0.10
0.05
Negative Logits
disreg
-0.95
friable
-0.94
suscep
-0.88
impra
-0.83
cryst
-0.80
follic
-0.79
">...
-0.78
unden
-0.77
">“
-0.74
impractica
-0.74
POSITIVE LOGITS
<bos>
0.71
poliuret
0.67
Sı
0.65
Söz
0.62
manuten
0.60
Tér
0.58
Chambres
0.58
Cataluña
0.58
Atenas
0.58
Américas
0.58
Activations Density 0.460%