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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anh
    -0.07
     Donne
    -0.07
     exceedingly
    -0.06
     bigger
    -0.06
    IMP
    -0.06
    _interp
    -0.06
    ОН
    -0.06
    alse
    -0.06
    多地
    -0.06
     decades
    -0.06
    POSITIVE LOGITS
     Lucifer
    0.08
    触动
    0.07
     męż
    0.07
    恋情
    0.07
    ,lat
    0.07
    hua
    0.07
    碉
    0.07
    貊
    0.06
    إخ
    0.06
     труб
    0.06
    Act Density 0.035%

    No Known Activations