INDEX
Explanations
references to automobile accidents and their details
New Auto-Interp
Negative Logits
errupted
-0.15
murderers
-0.15
æĭĶ
-0.14
murdering
-0.14
Killing
-0.14
нки
-0.14
Guns
-0.13
murdered
-0.13
dbg
-0.13
Shooter
-0.13
POSITIVE LOGITS
acc
0.38
crash
0.34
Acc
0.34
accident
0.34
_acc
0.33
Acc
0.33
acc
0.32
collision
0.32
accidents
0.31
wreck
0.31
Activations Density 0.049%