INDEX
Explanations
references to historical government policies, specifically the New Deal
references to the New Deal
New Auto-Interp
Negative Logits
untu
-0.72
ccess
-0.70
RAFT
-0.69
ĺħ
-0.69
ichen
-0.67
asus
-0.67
gotten
-0.66
thodox
-0.65
lé
-0.64
umn
-0.61
POSITIVE LOGITS
ership
1.48
deal
1.19
Deal
1.16
Deal
1.16
deals
0.90
deals
0.88
Deals
0.87
buster
0.82
etta
0.80
ers
0.79
Activations Density 0.014%