INDEX
Explanations
references to supermarket chains and their sustainability ratings
New Auto-Interp
Negative Logits
imon
-0.18
gross
-0.16
achs
-0.13
wdx
-0.13
ÑĢоÑī
-0.13
affe
-0.13
aepernick
-0.13
lacak
-0.13
enson
-0.13
ilters
-0.13
POSITIVE LOGITS
rating
0.63
ratings
0.57
score
0.54
Rating
0.52
Rating
0.48
rating
0.48
scores
0.47
-rating
0.47
Ratings
0.46
score
0.45
Activations Density 0.174%