INDEX
Explanations
mentions of instances of bombing
occurrences of the word "bombing."
New Auto-Interp
Negative Logits
laus
-0.97
ITY
-0.73
eva
-0.73
learn
-0.71
Lear
-0.70
Tang
-0.69
mia
-0.68
mis
-0.67
Values
-0.66
los
-0.66
POSITIVE LOGITS
bombing
1.20
bombings
1.04
raids
1.03
spree
0.95
barr
0.94
bomber
0.92
bombers
0.88
raid
0.84
bombard
0.84
bombardment
0.82
Activations Density 0.023%