INDEX
Explanations
phrases that express possession or necessity
New Auto-Interp
Negative Logits
itſelf
-1.21
myſelf
-1.12
Monfieur
-1.01
themſelves
-1.01
himſelf
-0.99
ſtate
-0.97
ainfi
-0.97
becauſe
-0.96
againſt
-0.94
purpoſe
-0.94
POSITIVE LOGITS
a
1.26
had
1.12
an
1.11
had
1.01
HAD
1.01
HAD
0.96
Had
0.94
have
0.93
have
0.92
0.91
Activations Density 0.335%