INDEX
Explanations
terms and references related to economics and economic concepts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.25
1.5%
352
+0.12
0.7%
219
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
460
+0.25
0.01
156
+0.12
0.01
352
+0.12
0.01
Negative Logits
thood
-1.60
TING
-1.51
)](#
-1.45
_________
-1.44
negative
-1.42
]>
-1.40
rapy
-1.40
happier
-1.40
ricanes
-1.38
positive
-1.34
POSITIVE LOGITS
burg
1.67
¡
1.65
yard
1.64
hoe
1.56
sake
1.55
aurus
1.55
qua
1.54
ume
1.50
must
1.47
acia
1.47
Activations Density 0.025%