INDEX
Explanations
repeated references to the speaker's personal experiences or actions
New Auto-Interp
Negative Logits
TargetException
-0.79
miniaturka
-0.78
indígen
-0.75
onPostExecute
-0.74
]")]
-0.73
purpoſe
-0.73
increí
-0.72
témoig
-0.70
colgante
-0.70
estadounid
-0.68
POSITIVE LOGITS
us
0.47
ville
0.36
nás
0.34
ourselves
0.34
テッド
0.34
↵↵
0.33
us
0.33
rs
0.32
сме
0.32
ợ
0.32
Activations Density 0.118%