INDEX
Explanations
prepositions indicating time or location
New Auto-Interp
Negative Logits
itſelf
-1.16
Majefty
-0.98
Houſe
-0.93
thri
-0.86
Hezbollah
-0.85
Perſ
-0.84
himſelf
-0.83
themſelves
-0.81
Chriftian
-0.81
houſe
-0.81
POSITIVE LOGITS
FROM
1.44
FROM
1.35
From
1.27
Từ
1.25
Từ
1.23
from
1.20
từ
1.19
dari
1.17
Από
1.11
From
1.10
Activations Density 0.001%