INDEX
Explanations
expressions related to affection or admiration for a particular entity or activity
phrases that express various forms of love or affection
New Auto-Interp
Negative Logits
aunder
-1.01
DragonMagazine
-0.89
alion
-0.84
ratulations
-0.82
soDeliveryDate
-0.81
acent
-0.79
helm
-0.78
wcs
-0.77
eworks
-0.76
VS
-0.75
POSITIVE LOGITS
automobiles
0.91
motorcycles
0.88
sweets
0.85
tink
0.84
hobbies
0.83
adventure
0.81
outdoors
0.81
aesthetics
0.80
preserving
0.80
music
0.80
Activations Density 0.213%