INDEX
Explanations
expressions of change or evolution over time
New Auto-Interp
Negative Logits
Eventually
-0.17
ultimate
-0.17
Eventually
-0.17
orthy
-0.15
ultimately
-0.15
eventually
-0.14
ultimate
-0.14
atsu
-0.14
IO
-0.14
èIJ
-0.14
POSITIVE LOGITS
now
0.22
now
0.19
again
0.18
instead
0.16
tiên
0.16
ahora
0.16
lại
0.16
iki
0.15
intervening
0.15
ocht
0.15
Activations Density 0.124%