INDEX
Explanations
occurrences of the word "around" in various contexts
New Auto-Interp
Negative Logits
apult
-0.15
ermann
-0.15
pod
-0.15
mbH
-0.15
à¥įवर
-0.14
Bis
-0.14
isc
-0.14
Caesar
-0.14
linear
-0.14
orian
-0.14
POSITIVE LOGITS
corners
0.19
kur
0.17
-around
0.17
circumference
0.16
quanh
0.16
roud
0.15
ADER
0.15
ther
0.15
-clock
0.15
clock
0.15
Activations Density 0.101%