INDEX
Explanations
references to time periods, specifically the word "months" and variations of it
New Auto-Interp
Negative Logits
abbo
-0.16
emotion
-0.15
hr
-0.15
esta
-0.14
Gros
-0.14
polit
-0.14
dio
-0.13
tas
-0.13
em
-0.13
horm
-0.13
POSITIVE LOGITS
-long
0.15
esini
0.14
buie
0.14
trá»Ŀi
0.14
份
0.13
loub
0.13
okit
0.13
.advance
0.13
YPES
0.13
adow
0.13
Activations Density 0.026%