INDEX
Explanations
references to the concept of "around" in relation to location or time
New Auto-Interp
Negative Logits
urb
-0.16
amine
-0.16
eros
-0.15
.wp
-0.15
inki
-0.14
owell
-0.14
zig
-0.14
ux
-0.14
aters
-0.14
etes
-0.14
POSITIVE LOGITS
-the
0.27
abouts
0.21
thew
0.19
s
0.18
trip
0.18
ìŀ¡
0.18
/about
0.17
/by
0.17
issement
0.17
/on
0.16
Activations Density 0.046%