INDEX
Explanations
dates or days of the week
references to the day "Thursday" in various contexts
New Auto-Interp
Negative Logits
ership
-0.83
chest
-0.82
pend
-0.77
arist
-0.76
audi
-0.74
ebook
-0.74
eas
-0.74
respons
-0.74
abet
-0.68
ates
-0.68
POSITIVE LOGITS
morning
1.47
afternoon
1.45
evening
1.31
mornings
1.23
night
1.22
Night
1.10
nights
1.07
evenings
1.06
morning
0.99
Friday
0.88
Activations Density 0.036%