INDEX
Explanations
phrases indicating time or duration of past events
New Auto-Interp
Negative Logits
æľ«
-0.15
ogan
-0.15
ãĥ£
-0.15
ernes
-0.15
ÄŁan
-0.15
arts
-0.15
ungi
-0.14
rone
-0.14
Packs
-0.14
erner
-0.14
POSITIVE LOGITS
few
0.23
/current
0.17
decade
0.17
several
0.16
åĩł
0.16
неÑģколÑĮко
0.15
OnInit
0.15
three
0.15
Few
0.15
two
0.15
Activations Density 0.041%