INDEX
Explanations
mentions of the ABC television network and its news segments
New Auto-Interp
Negative Logits
owy
-0.17
agen
-0.17
NESS
-0.16
age
-0.15
Sphere
-0.15
ussia
-0.15
ocha
-0.15
udur
-0.14
ILED
-0.14
uder
-0.14
POSITIVE LOGITS
enson
0.19
DEF
0.18
OLUTE
0.17
ridged
0.17
mouse
0.16
XYZ
0.15
_xyz
0.15
Family
0.15
illez
0.15
ABC
0.14
Activations Density 0.014%