INDEX
Explanations
instances of the word "today" and related expressions indicating the present
New Auto-Interp
Negative Logits
ly
-0.17
åύ
-0.15
,
-0.14
ple
-0.14
ences
-0.14
ocker
-0.14
naire
-0.14
年代
-0.13
Hlav
-0.13
Invoker
-0.13
POSITIVE LOGITS
aday
0.21
hôm
0.19
########.
0.16
732
0.16
odor
0.16
-day
0.16
گار
0.15
eÄį
0.15
BASIS
0.15
lush
0.15
Activations Density 0.047%