INDEX
Explanations
state of being or possession
New Auto-Interp
Negative Logits
deviennent
0.49
possano
0.46
pouvaient
0.44
становятся
0.43
puedan
0.42
なくなる
0.41
puissent
0.40
possono
0.39
diventa
0.38
podían
0.37
POSITIVE LOGITS
belongs
0.75
resides
0.71
belong
0.68
possesses
0.64
belonged
0.63
owns
0.61
reside
0.61
is
0.57
находится
0.56
είναι
0.56
Activations Density 0.034%