INDEX
Explanations
occurrences of injuries and incidents involving burns or cuts
New Auto-Interp
Negative Logits
icio
-0.16
opro
-0.16
anzi
-0.15
à¹Īà¸Ńà¸ĩ
-0.15
andır
-0.15
поÑĪ
-0.14
werk
-0.14
ibil
-0.14
dete
-0.14
xbe
-0.14
POSITIVE LOGITS
uppy
0.15
duk
0.15
injury
0.14
пÑĢиÑģÑĤÑĥп
0.14
Fallen
0.14
ึà¸ģ
0.14
falling
0.14
Bod
0.14
forget
0.14
gaard
0.14
Activations Density 0.191%