INDEX
Explanations
commercial advertisements
instances of the word "Advertisement"
New Auto-Interp
Negative Logits
<-
-0.80
-
-0.64
–
-0.60
/
-0.59
util
-0.59
..
-0.59
later
-0.58
forward
-0.58
fue
-0.56
hall
-0.56
POSITIVE LOGITS
Advertisement
4.14
SPONSORED
2.59
Newsletter
2.27
ADVERTISEMENT
1.84
advertisement
1.84
advertising
1.53
RELATED
1.41
Enlarge
1.33
Photo
1.25
PHOTOS
1.24
Activations Density 0.019%