INDEX
Explanations
phrases that indicate topics or subjects being discussed
"as for" followed by a topic
New Auto-Interp
Negative Logits
nemlig
-0.59
uxxxx
-0.59
ensement
-0.58
RetentionPolicy
-0.53
totiž
-0.53
Filmografie
-0.51
SharedCtor
-0.51
astfel
-0.51
élevées
-0.49
namelijk
-0.49
POSITIVE LOGITS
other
0.91
Elsewhere
0.78
Other
0.77
other
0.76
Other
0.76
Others
0.72
其他的
0.71
OTHER
0.70
others
0.69
OTHER
0.68
Activations Density 0.309%