INDEX
Explanations
phrases indicating significant societal changes or transformations
New Auto-Interp
Negative Logits
lihood
-0.76
Plex
-0.71
kered
-0.71
Shape
-0.71
asonic
-0.67
Rect
-0.67
nton
-0.67
tle
-0.65
romy
-0.65
��
-0.65
POSITIVE LOGITS
lees
0.74
inactive
0.73
comments
0.69
ao
0.68
retired
0.68
れ
0.67
subscribers
0.66
cheaply
0.66
reprint
0.65
retire
0.64
Activations Density 0.064%