INDEX
Explanations
temporal markers and indicators within the text
New Auto-Interp
Negative Logits
ingles
-0.15
geb
-0.15
actories
-0.14
ucks
-0.14
nim
-0.14
ôn
-0.14
веÑģÑĤи
-0.13
krit
-0.13
bole
-0.13
Session
-0.13
POSITIVE LOGITS
celik
0.16
ISTER
0.15
Pool
0.15
Redistributions
0.14
iola
0.14
olini
0.14
uez
0.14
lingen
0.14
endas
0.13
Ïĩεία
0.13
Activations Density 0.505%