INDEX
Explanations
phrases related to advertisements
references to advertisements
New Auto-Interp
Negative Logits
ĨĴ
-0.94
bred
-0.79
lihood
-0.77
20439
-0.76
Jr
-0.73
Caribbean
-0.71
Dice
-0.69
Cyprus
-0.69
otype
-0.68
ppo
-0.68
POSITIVE LOGITS
vertising
1.07
ads
1.00
verts
0.93
advertising
0.89
strip
0.88
elaide
0.87
vertis
0.87
nause
0.86
billboards
0.82
ieu
0.82
Activations Density 0.021%