INDEX
Explanations
references to the sport of Ultimate, related terms and entities like players, coaches, and teams
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.14
0.4%
227
+0.13
0.4%
1870
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.14
0.08
1870
+0.13
0.04
783
+0.11
0.04
Negative Logits
municipi
-0.78
Și
-0.76
StoryboardSegue
-0.75
arrivant
-0.74
Trayectoria
-0.74
المعيارى
-0.73
ⓧ
-0.72
Уважаемые
-0.72
sogget
-0.71
tonode
-0.71
POSITIVE LOGITS
McLaugh
0.96
apprehen
0.91
gaily
0.84
McInt
0.83
Daven
0.78
unspeak
0.78
Vaugh
0.78
shenan
0.78
sophistic
0.74
pooh
0.74
Activations Density 0.723%