INDEX
Explanations
themes related to creativity and representation in media
New Auto-Interp
Negative Logits
senal
-0.14
TableCell
-0.14
HeaderCode
-0.14
ì©
-0.14
NewProp
-0.14
COPE
-0.13
reff
-0.13
åłĤ
-0.13
membr
-0.13
iras
-0.13
POSITIVE LOGITS
female
0.22
gender
0.19
male
0.18
feminine
0.17
females
0.17
older
0.17
female
0.17
younger
0.16
ühl
0.16
women
0.16
Activations Density 0.226%