INDEX
Explanations
actions and interactions involving people, particularly greetings and handshakes in social contexts
New Auto-Interp
Negative Logits
ÑĩаÑģ
-0.17
gba
-0.15
)NULL
-0.15
bern
-0.14
é³´
-0.14
/Dk
-0.14
iê
-0.14
ë°
-0.14
-urlencoded
-0.13
erras
-0.13
POSITIVE LOGITS
eck
0.19
ook
0.16
à¸ģำล
0.15
shortly
0.14
ooth
0.14
tet
0.13
ipl
0.13
aint
0.13
facet
0.13
unidentified
0.13
Activations Density 0.059%