INDEX
Explanations
phrases related to physical activity, particularly running
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.20
1.2%
410
+0.11
0.6%
555
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
47
+0.20
0.06
410
+0.11
0.06
976
+0.10
0.05
Negative Logits
<bos>
-3.21
dev
-0.73
AssemblyCompany
-0.72
const
-0.71
expect
-0.70
HasColumnType
-0.69
HasColumnName
-0.69
بالإنجليزية
-0.68
HasIndex
-0.67
console
-0.67
POSITIVE LOGITS
increa
2.52
affor
2.44
impra
2.21
maneu
2.17
emphat
2.15
Juf
2.12
accla
2.10
swarovski
2.07
reluct
2.06
unwarran
2.06
Activations Density 0.231%