INDEX
Explanations
references to physical body parts, especially fingers
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.9%
1926
+0.12
0.6%
1363
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1363
+0.16
0.03
1926
+0.12
0.03
1425
+0.10
0.02
Negative Logits
<bos>
-2.99
PeEnEo
-0.82
Enllaces
-0.80
CreateMap
-0.77
})();
-0.70
SourceChecksum
-0.70
</thead>
-0.69
public
-0.68
HostException
-0.68
CodeDom
-0.67
POSITIVE LOGITS
increa
1.93
impractica
1.87
ecru
1.85
fta
1.84
disagre
1.81
stockholm
1.80
impra
1.80
maneu
1.79
madonna
1.79
affor
1.78
Activations Density 0.111%