INDEX
Explanations
phrases related to sports teams and their operations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1253
+0.16
0.5%
108
+0.12
0.4%
80
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
392
+0.16
0.03
576
+0.12
0.04
175
+0.09
0.06
Negative Logits
spli
-0.58
medes
-0.58
nare
-0.55
DBNull
-0.55
autorisation
-0.54
EINVAL
-0.54
poft
-0.52
ophosph
-0.52
sfera
-0.51
manj
-0.50
POSITIVE LOGITS
racon
0.64
chanteuse
0.63
beurre
0.62
mediocrity
0.62
Messieurs
0.61
murm
0.59
gilet
0.58
hoody
0.58
serai
0.57
chante
0.57
Activations Density 0.549%