INDEX
Explanations
phrases related to physical altercation or combat sports
New Auto-Interp
Negative Logits
.IntPtr
-0.16
quete
-0.15
lis
-0.15
Kills
-0.15
ÏĢÎŃ
-0.15
gaard
-0.14
stable
-0.14
azzo
-0.14
aby
-0.14
_malloc
-0.14
POSITIVE LOGITS
punch
0.28
punches
0.27
hay
0.24
KO
0.23
punching
0.21
punched
0.21
Punch
0.21
landed
0.21
knockout
0.20
ko
0.20
Activations Density 0.024%