INDEX
Explanations
references to the McDonald's brand
New Auto-Interp
Negative Logits
lessly
-0.17
ä¿®
-0.15
ored
-0.15
uned
-0.15
uning
-0.14
eten
-0.14
æ¥
-0.14
cura
-0.14
eward
-0.13
aret
-0.13
POSITIVE LOGITS
intosh
0.20
onald
0.19
iece
0.18
ization
0.16
ize
0.16
ald
0.16
agh
0.16
spor
0.16
andles
0.15
voy
0.15
Activations Density 0.005%