INDEX
Explanations
words related to sales or commercial success
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
609
+0.08
0.2%
1013
+0.08
0.2%
783
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1854
+0.08
0.03
783
+0.08
0.03
1834
+0.08
0.03
Negative Logits
ftu
-1.73
thut
-1.71
fup
-1.69
fta
-1.67
mef
-1.54
tranf
-1.53
fep
-1.53
fte
-1.51
aen
-1.50
»>
-1.49
POSITIVE LOGITS
sales
0.77
worldwide
0.74
sell
0.66
sold
0.64
selling
0.61
sold
0.59
sales
0.59
selling
0.57
Sales
0.57
sells
0.56
Activations Density 0.363%