INDEX
Explanations
travel, hotels, restaurants
New Auto-Interp
Negative Logits
签字
0.55
_
0.54
<0x0D>
0.52
书
0.51
报错
0.51
ورک
0.49
这不是
0.49
Concern
0.49
Rhet
0.49
June
0.48
POSITIVE LOGITS
Expedia
0.75
hotels
0.74
restaurants
0.72
restoran
0.72
restaurantes
0.70
gastronom
0.67
menikmati
0.67
hotel
0.66
sightseeing
0.66
ресторан
0.65
Activations Density 0.043%