INDEX
Explanations
phrases related to change and deterioration over time
New Auto-Interp
Negative Logits
ergus
-0.16
itou
-0.14
atype
-0.14
adow
-0.14
lda
-0.13
ampo
-0.13
óng
-0.13
iry
-0.13
nelly
-0.13
indow
-0.13
POSITIVE LOGITS
time
0.53
æĹ¶éĹ´
0.38
time
0.37
.time
0.34
overtime
0.33
Time
0.32
_time
0.32
æĻĤéĸĵ
0.31
vertime
0.31
time
0.30
Activations Density 0.227%