EXPLANATIONS
[冠] => [冠]
INFERENCE
IFRAME INTEGRATION
NEGATIVE LOGITS
_sure-15.063
�-13.938
_gran-13.375
겨-13.375
ุง-13.250
té-13.188
_ordered-13.125
冲动-12.563
前途-12.563
_vọng-12.500
POSITIVE LOGITS
matching17.750
logical17.625
lap17.500
ogenic17.000
edBy16.875
er16.375
.Fill16.125
shelf15.938
edin15.813
ści15.750
ACTIVATION TIMES 0.0137%
Activation histogram is not available.
Logits histogram is not available.
TOPACTIVATIONS
SUBSAMPLING80%
SUBSAMPLING60%
SUBSAMPLING40%
NONACTIVATING