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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    酞
    -0.07
     sustained
    -0.07
     unintended
    -0.06
    angling
    -0.06
    成人
    -0.06
     assassin
    -0.06
     Titles
    -0.06
     tahun
    -0.06
    modele
    -0.06
    不同程度
    -0.06
    POSITIVE LOGITS
     constantly
    0.07
    ureka
    0.07
     pointless
    0.07
    分开
    0.07
     form
    0.06
     principles
    0.06
     yo
    0.06
    杯子
    0.06
     Lemma
    0.06
     Nap
    0.06
    Act Density 0.005%

    No Known Activations