Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    恨不得
    -0.07
    Training
    -0.07
     betrayed
    -0.07
     resemblance
    -0.07
    	day
    -0.07
    elenium
    -0.07
    读后感
    -0.07
    觖
    -0.07
     aVar
    -0.07
     strSQL
    -0.07
    POSITIVE LOGITS
    坐
    0.08
     ".");↵
    0.07
     pic
    0.07
    방
    0.07
    Fight
    0.07
     depict
    0.07
    .You
    0.07
    _fac
    0.07
     spe
    0.07
     ste
    0.07
    Act Density 0.006%

    No Known Activations