INDEX
Explanations
occurrences of the substring "ap" in various contexts within the text
New Auto-Interp
Negative Logits
iggers
-0.17
estate
-0.16
iad
-0.16
hod
-0.16
ิà¸ļ
-0.15
edList
-0.15
ctest
-0.15
preter
-0.15
croll
-0.15
anut
-0.15
POSITIVE LOGITS
oose
0.20
oor
0.20
pler
0.16
trap
0.16
ìŀIJ기
0.16
hton
0.16
148
0.15
thur
0.15
nik
0.15
uture
0.15
Activations Density 0.043%