INDEX
Explanations
words related to packages, parcels, and obsessively looking forward to receiving items
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1589
+0.11
0.4%
50
+0.10
0.4%
605
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1363
+0.11
0.04
1519
+0.10
0.04
260
+0.09
0.03
Negative Logits
<bos>
-2.39
AssemblyCompany
-0.73
Código
-0.72
Comer
-0.71
Explicación
-0.71
भार
-0.70
Kontrola
-0.68
NSCoder
-0.67
PerformLayout
-0.67
Ша
-0.66
POSITIVE LOGITS
stockholm
2.03
increa
1.95
strick
1.94
volunte
1.91
impra
1.90
swarovski
1.89
fortn
1.89
scrat
1.87
casio
1.85
leonardo
1.83
Activations Density 0.305%