INDEX
Explanations
Weekends mentioned in the text
references to weekends and Saturday activities
New Auto-Interp
Negative Logits
inscribed
-0.65
ption
-0.65
ce
-0.63
Sphere
-0.62
ity
-0.61
ness
-0.61
ana
-0.60
Pose
-0.60
ody
-0.60
ius
-0.59
POSITIVE LOGITS
weekends
3.94
Saturdays
2.44
Sundays
2.33
evenings
2.26
Fridays
1.96
mornings
1.90
nights
1.87
weekend
1.83
Mondays
1.78
aturdays
1.72
Activations Density 0.011%