INDEX
Explanations
phrases related to the duration of experiences or time periods
New Auto-Interp
Negative Logits
uur
-0.18
ourg
-0.17
леÑĤ
-0.15
allax
-0.14
uetype
-0.13
inkel
-0.13
é¾
-0.13
268
-0.13
ogi
-0.13
treff
-0.13
POSITIVE LOGITS
spent
0.17
spent
0.17
ago
0.15
chers
0.15
ÛĮاÙĨ
0.15
vant
0.14
ulos
0.14
MBER
0.14
ynchronized
0.14
esine
0.14
Activations Density 0.113%