INDEX
Explanations
references to political actions and sentiments surrounding abortion debates
New Auto-Interp
Negative Logits
Ekon
-0.18
alytics
-0.17
arium
-0.16
ìķĮ볤
-0.16
erken
-0.15
avad
-0.15
elfast
-0.15
ãĢ
-0.14
essional
-0.14
FETCH
-0.14
POSITIVE LOGITS
Fine
0.39
Fi
0.36
Fi
0.34
Fine
0.32
fine
0.28
TD
0.28
FG
0.25
FF
0.24
FINE
0.24
fi
0.24
Activations Density 0.020%