INDEX
Explanations
references to Joe Biden and his political actions and statements
New Auto-Interp
Negative Logits
aub
-0.18
vale
-0.17
anine
-0.16
inea
-0.15
enna
-0.15
orer
-0.15
unda
-0.15
Enlarge
-0.15
sd
-0.14
pike
-0.14
POSITIVE LOGITS
ior
0.18
omics
0.17
261
0.16
780
0.16
anden
0.16
ium
0.15
este
0.14
116
0.14
.jupiter
0.13
etti
0.13
Activations Density 0.007%