INDEX
Explanations
themes related to familial relationships and societal expectations
New Auto-Interp
Negative Logits
attract
-0.15
itia
-0.14
ocide
-0.14
æİī
-0.14
COPE
-0.14
coordinate
-0.13
timestamps
-0.13
unist
-0.13
miss
-0.13
teg
-0.13
POSITIVE LOGITS
demands
0.23
demand
0.23
demanded
0.23
pressure
0.23
demand
0.23
force
0.23
pressures
0.22
forces
0.22
forb
0.22
-pressure
0.22
Activations Density 0.440%