INDEX
Explanations
themes of societal struggle and critique regarding agency and public service issues
New Auto-Interp
Negative Logits
_MAXIMUM
-0.15
stru
-0.15
ith
-0.14
hack
-0.14
Lans
-0.13
iona
-0.13
ocracy
-0.13
ela
-0.13
ürn
-0.13
Auth
-0.13
POSITIVE LOGITS
emy
0.17
477
0.16
ahlen
0.15
suddenly
0.15
[now
0.14
ATOR
0.14
enser
0.14
469
0.14
now
0.14
enstein
0.14
Activations Density 0.226%