INDEX
Explanations
references to supporting local initiatives or businesses
New Auto-Interp
Negative Logits
andle
-0.19
ÑĨеÑĢ
-0.15
nuts
-0.14
nut
-0.14
_LOWER
-0.13
worsh
-0.13
577
-0.13
AMP
-0.13
andon
-0.13
ees
-0.13
POSITIVE LOGITS
support
0.59
support
0.52
supporting
0.52
supports
0.52
Support
0.51
Support
0.50
Supporting
0.48
supports
0.47
-support
0.47
Supports
0.45
Activations Density 0.286%