INDEX
Explanations
dates and timestamps in the text
New Auto-Interp
Negative Logits
bjerg
-0.18
جاÙĨ
-0.16
Gardner
-0.15
Heb
-0.15
legen
-0.15
actable
-0.14
erre
-0.14
ereum
-0.14
EDGE
-0.14
rient
-0.13
POSITIVE LOGITS
Boh
0.15
kees
0.14
ado
0.14
_BO
0.14
Quote
0.14
æ°ĹæĮģãģ¡
0.14
ango
0.14
videa
0.13
grass
0.13
agli
0.13
Activations Density 0.131%