EXPLANATIONS
[study] => [of]
INFERENCE
IFRAME INTEGRATION
NEGATIVE LOGITS
plies-17.500
�-15.125
カー-14.938
_recurs-14.688
连云-14.125
iser-13.938
_recycle-13.875
ote-13.813
_Accum-13.813
imizer-13.625
POSITIVE LOGITS
孺18.750
嵯15.875
oval15.313
_fundamentals15.125
_minimum15.125
根底15.063
sWith14.688
atron14.625
_Mothers14.250
镫13.938
ACTIVATION TIMES 0.0812%
Activation histogram is not available.
Logits histogram is not available.
TOPACTIVATIONS
SUBSAMPLING80%
SUBSAMPLING60%
SUBSAMPLING40%
NONACTIVATING