INDEX
Explanations
references to the speaker's personal experiences or possessions
New Auto-Interp
Negative Logits
itſelf
-1.59
themſelves
-1.30
Houſe
-1.26
Efq
-1.24
Monfieur
-1.23
Reſ
-1.22
himſelf
-1.17
raiſ
-1.16
Anſ
-1.08
againſt
-1.07
POSITIVE LOGITS
my
1.75
My
1.70
MY
1.40
My
1.39
my
1.37
getMy
1.21
I
1.12
我的
1.11
MY
1.10
我的
1.09
Activations Density 0.071%