INDEX
Explanations
references to community and daily life interactions
New Auto-Interp
Negative Logits
uitka
-0.18
ermen
-0.17
LOPT
-0.16
gili
-0.14
ngo
-0.14
ivism
-0.14
/setup
-0.14
ogene
-0.14
aya
-0.14
udget
-0.14
POSITIVE LOGITS
daily
0.23
living
0.23
everyday
0.22
consume
0.21
consumption
0.20
consumes
0.19
consuming
0.19
eats
0.18
eat
0.18
eating
0.18
Activations Density 0.229%