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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Discipline
    -0.08
    wine
    -0.08
    VIRTUAL
    -0.07
    fair
    -0.07
    蛇
    -0.07
    雀
    -0.07
    _ADV
    -0.07
    paid
    -0.07
     each
    -0.07
     adulte
    -0.07
    POSITIVE LOGITS
     hmm
    0.07
     upload
    0.07
    etheless
    0.06
     smoothing
    0.06
    召回
    0.06
     №
    0.06
    热
    0.06
     mph
    0.06
    婻
    0.06
     fotoğ
    0.06
    Act Density 0.000%

    No Known Activations