INDEX
Explanations
dates and calendar-related terms
New Auto-Interp
Negative Logits
[];
-0.88
;
-0.84
';
-0.81
";
-0.74
`;
-0.73
"";
-0.70
'';
-0.69
();
-0.69
;
-0.67
){
-0.65
POSITIVE LOGITS
↵
1.03
itſelf
0.97
himſelf
0.91
themſelves
0.89
Jefus
0.89
myſelf
0.88
ſelves
0.81
Monfieur
0.81
becauſe
0.80
ſeveral
0.79
Activations Density 0.438%