INDEX
Explanations
phrases related to skateboarding and hockey
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1350
+0.24
1.2%
795
+0.16
0.8%
1092
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1350
+0.24
0.04
795
+0.16
0.04
690
+0.13
0.03
Negative Logits
kuku
-0.69
rescin
-0.67
laim
-0.65
posteriorly
-0.64
zara
-0.63
traktor
-0.63
interposed
-0.63
condense
-0.61
coerce
-0.60
equalled
-0.59
POSITIVE LOGITS
skating
1.05
skate
1.02
Hockey
0.95
skates
0.94
hockey
0.93
Skate
0.92
Skate
0.88
Skating
0.87
rink
0.86
Hockey
0.83
Activations Density 0.434%