INDEX
Explanations
phrases that express necessity or obligation
New Auto-Interp
Negative Logits
amen
-0.17
ertia
-0.16
ález
-0.15
uje
-0.14
eah
-0.14
Jennings
-0.14
DeÄŁ
-0.14
isp
-0.14
Dispatch
-0.13
amber
-0.13
POSITIVE LOGITS
pper
0.17
vars
0.16
Raised
0.16
licht
0.16
raised
0.15
udder
0.15
gaard
0.15
Moff
0.15
andan
0.15
ibble
0.15
Activations Density 0.022%