INDEX
Explanations
references to time-related concepts, specifically clocks and time-keeping activities
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2004
+0.15
0.6%
1363
+0.12
0.5%
1516
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1516
+0.15
0.02
2004
+0.12
0.02
67
+0.12
0.02
Negative Logits
banane
-0.68
cannes
-0.65
sopr
-0.65
diamant
-0.64
intermitt
-0.63
+++++
-0.62
Marit
-0.61
chré
-0.60
lidl
-0.59
Squal
-0.59
POSITIVE LOGITS
clock
1.61
clock
1.47
clocks
1.43
Clock
1.37
Clock
1.30
CLOCK
1.18
CLOCK
1.15
clocked
1.01
Clocks
0.99
reloj
0.82
Activations Density 0.079%