INDEX
Explanations
phrases related to economic aspects like sanctions, market competition, and oil prices
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.24
0.7%
1385
+0.12
0.4%
678
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1870
+0.24
0.06
678
+0.12
0.06
74
+0.12
0.04
Negative Logits
shenan
-1.81
gaily
-1.69
reluct
-1.67
unspeak
-1.64
snoopy
-1.62
impra
-1.61
depic
-1.60
ineffec
-1.58
intersper
-1.58
apprehen
-1.57
POSITIVE LOGITS
raught
0.75
marginVertical
0.62
furg
0.60
JEL
0.60
flexGrow
0.59
hadas
0.58
momentos
0.57
marginHorizontal
0.57
platos
0.56
vinos
0.56
Activations Density 0.576%