INDEX
Explanations
references to academic or military institutions
terms related to educational institutions, particularly military or training academies
New Auto-Interp
Negative Logits
oran
-0.75
Bundy
-0.74
Panic
-0.71
STON
-0.67
ter
-0.67
Arcade
-0.67
pour
-0.66
istani
-0.65
patrick
-0.63
ppy
-0.62
POSITIVE LOGITS
academy
1.01
acad
0.92
emies
0.87
corps
0.83
acas
0.75
liga
0.75
disadvant
0.74
onte
0.73
vit
0.70
ingred
0.69
Activations Density 0.016%