INDEX
Explanations
words related to energy and oil prices
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1356
+0.09
0.2%
856
+0.09
0.2%
1445
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1795
+0.09
0.03
1241
+0.09
0.03
965
+0.08
0.03
Negative Logits
emphat
-1.56
wien
-1.55
strick
-1.55
fuf
-1.53
increa
-1.51
effe
-1.51
reluct
-1.50
maneu
-1.49
inev
-1.47
impra
-1.46
POSITIVE LOGITS
prices
1.08
price
0.93
price
0.83
Prices
0.81
prices
0.77
Prices
0.75
pricing
0.74
Price
0.72
Price
0.71
priced
0.69
Activations Density 0.208%