INDEX
Explanations
activities and experiences centered around relaxation and enjoyment in social settings
New Auto-Interp
Negative Logits
277
-0.14
998
-0.14
uers
-0.14
Ahead
-0.14
regular
-0.14
stad
-0.14
ìĹĩ
-0.13
regular
-0.13
opr
-0.13
ź
-0.13
POSITIVE LOGITS
while
0.31
while
0.28
_while
0.26
whilst
0.26
WHILE
0.24
While
0.22
while
0.21
mentre
0.21
mientras
0.20
While
0.20
Activations Density 0.189%