INDEX
Explanations
incidents involving animal attacks
New Auto-Interp
Negative Logits
μι
-0.16
Bom
-0.15
RAIN
-0.15
ninger
-0.15
रत
-0.14
uel
-0.14
é¼ł
-0.14
å¹¹
-0.14
erce
-0.14
eskort
-0.14
POSITIVE LOGITS
bite
0.51
bites
0.50
Bite
0.42
biting
0.40
bite
0.40
bitten
0.39
attack
0.32
attacks
0.29
byte
0.29
attacking
0.27
Activations Density 0.067%