INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
ay
1.23
ان
1.12
smoke
1.09
CE
1.08
ag
1.07
OS
1.05
smoke
1.05
OM
1.04
ON
1.02
حالی
0.97
POSITIVE LOGITS
Water
1.88
acqua
1.77
irrig
1.73
água
1.70
agua
1.58
water
1.56
Wasser
1.56
waters
1.54
水を
1.54
水
1.53
Activations Density 0.409%