INDEX
Explanations
expressions of intention or future actions
New Auto-Interp
Negative Logits
kla
-0.18
ÙĴس
-0.15
chez
-0.14
vow
-0.14
oday
-0.14
Ñĥй
-0.14
eÅŁ
-0.14
atos
-0.14
åIJ§
-0.14
beforeSend
-0.14
POSITIVE LOGITS
eventual
0.21
soon
0.19
next
0.19
possible
0.18
eventually
0.18
imminent
0.18
possibly
0.18
soon
0.17
upcoming
0.16
possibile
0.16
Activations Density 0.056%