INDEX
Explanations
references to television and media consumption
New Auto-Interp
Negative Logits
itar
-0.15
itm
-0.14
å£
-0.13
ÙĪÚ©
-0.13
uracy
-0.13
ìĽħ
-0.13
Robotics
-0.13
amodel
-0.13
Tumblr
-0.13
ermal
-0.13
POSITIVE LOGITS
TV
0.96
television
0.91
tv
0.85
TV
0.83
Tv
0.77
Television
0.76
tv
0.71
-TV
0.69
_TV
0.68
_tv
0.66
Activations Density 0.312%