INDEX
Explanations
occurrences of the word "article" and its variations in the text
New Auto-Interp
Negative Logits
erken
-0.17
esc
-0.17
wards
-0.17
er
-0.16
aping
-0.16
-0.15
çİĩ
-0.15
soever
-0.15
illing
-0.15
ern
-0.14
POSITIVE LOGITS
ificial
0.18
anship
0.17
ifacts
0.17
/video
0.16
-length
0.16
hip
0.16
otle
0.15
Ń
0.15
asure
0.15
ãĥ¥
0.15
Activations Density 0.022%