INDEX
Explanations
expressions of hope and aspiration
New Auto-Interp
Negative Logits
almost
-0.21
almost
-0.19
Almost
-0.17
Almost
-0.17
uesta
-0.16
ahan
-0.15
.cli
-0.15
_almost
-0.15
otor
-0.14
bjerg
-0.14
POSITIVE LOGITS
soon
0.20
somehow
0.20
algún
0.19
alespoÅĪ
0.18
enough
0.18
alguna
0.17
Soon
0.17
ção
0.17
someday
0.17
soon
0.16
Activations Density 0.120%