INDEX
Explanations
people's names
mentions of specific individuals, particularly with the surname 'O'Brien' and its variants
New Auto-Interp
Negative Logits
pes
-0.69
ku
-0.62
Nap
-0.62
rises
-0.61
meric
-0.60
unhealthy
-0.59
cures
-0.58
ilial
-0.58
PV
-0.57
Moroc
-0.57
POSITIVE LOGITS
patrick
0.94
TD
0.78
TD
0.78
shire
0.75
hler
0.75
tainment
0.73
ysis
0.73
ument
0.72
ANCE
0.68
Neill
0.68
Activations Density 0.037%