INDEX
Explanations
expressions of love, interest, and passion across various contexts
New Auto-Interp
Negative Logits
GEBURTS
-0.71
IsContent
-0.67
#+#
-0.64
dimaksud
-0.63
générations
-0.62
aveug
-0.61
habituales
-0.61
hâte
-0.60
timbangkan
-0.60
ędziesz
-0.60
POSITIVE LOGITS
animals
0.76
music
0.70
horses
0.63
computers
0.62
languages
0.61
anything
0.61
outdoors
0.60
people
0.60
photography
0.58
sweets
0.58
Activations Density 0.264%