INDEX
Explanations
sentences containing the word "sometimes."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1964
+0.13
0.4%
1671
+0.12
0.4%
90
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1964
+0.13
0.04
1671
+0.12
0.04
69
+0.10
0.02
Negative Logits
alho
-0.58
meras
-0.57
sés
-0.57
InkWell
-0.56
FlatAppearance
-0.54
seny
-0.54
poliuret
-0.52
guir
-0.51
SwingConstants
-0.51
TextAlign
-0.50
POSITIVE LOGITS
shewn
0.97
fays
0.90
gaily
0.88
ftu
0.87
laft
0.86
perfon
0.85
tyme
0.83
fep
0.81
foon
0.80
fometimes
0.80
Activations Density 0.086%