INDEX
Explanations
instances of the word "now" and its variations, indicating a focus on present tense situations or current events
New Auto-Interp
Negative Logits
but
-0.16
urs
-0.15
ped
-0.15
unate
-0.15
er
-0.15
_ABI
-0.15
cken
-0.14
otherwise
-0.14
gne
-0.14
otherwise
-0.14
POSITIVE LOGITS
here
0.29
adays
0.25
HERE
0.21
imagine
0.19
withstanding
0.17
sıra
0.17
comes
0.17
_that
0.16
suddenly
0.14
UIP
0.14
Activations Density 0.030%