INDEX
Explanations
references to dates and numerical data related to months and years
New Auto-Interp
Negative Logits
-Jan
-0.21
Christmas
-0.18
jan
-0.18
11
-0.17
-Nov
-0.17
december
-0.17
christmas
-0.16
December
-0.16
JAN
-0.16
December
-0.15
POSITIVE LOGITS
August
0.18
Aug
0.18
August
0.17
ãĤ©
0.17
Aug
0.17
September
0.16
Sep
0.16
summer
0.16
AUG
0.16
aug
0.15
Activations Density 0.014%