INDEX
Explanations
instances of the word "then" indicating a sequence of events
New Auto-Interp
Negative Logits
sworth
-0.17
tingham
-0.17
اÙĦرÙħ
-0.16
ãĥ¼ãĥ«ãĥī
-0.16
illet
-0.15
atatype
-0.15
太éĥİ
-0.15
ieux
-0.15
patial
-0.15
oppable
-0.14
POSITIVE LOGITS
åŃ
0.16
¥
0.16
Verdana
0.15
agate
0.15
ger
0.15
ANCEL
0.15
clim
0.14
Calibri
0.14
ant
0.14
ottes
0.14
Activations Density 0.015%