INDEX
Explanations
phrases related to physics and measurements, specifically involving mass, distance, and gravitational force
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
284
+0.12
0.3%
690
+0.10
0.3%
1150
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
284
+0.12
0.07
2029
+0.10
0.04
1136
+0.09
0.04
Negative Logits
dises
-1.10
kado
-1.02
aen
-1.01
kram
-0.99
intenance
-0.97
hcm
-0.96
logis
-0.95
meis
-0.95
nece
-0.94
aspetta
-0.94
POSITIVE LOGITS
during
0.67
towards
0.60
throughout
0.59
Εκ
0.57
when
0.57
ariConfig
0.57
político
0.56
JCheckBox
0.56
toward
0.55
for
0.55
Activations Density 0.267%