INDEX
Explanations
phrases related to choking hazards
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1296
+0.11
0.4%
481
+0.11
0.4%
650
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
690
+0.11
0.03
1363
+0.11
0.03
1328
+0.10
0.03
Negative Logits
<bos>
-1.59
CreateMap
-0.85
},{
-0.71
}],
-0.69
AssemblyCompany
-0.69
للاسماء
-0.68
Giới
-0.66
GetAxis
-0.65
mkdirs
-0.65
Công
-0.65
POSITIVE LOGITS
affor
1.49
indestru
1.48
impra
1.41
unspeak
1.41
tolerably
1.36
increa
1.33
plenti
1.32
swarovski
1.29
stockholm
1.27
toledo
1.27
Activations Density 0.379%