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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mx
    -0.87
    ahime
    -0.77
    aucus
    -0.71
    ²¾
    -0.71
    zees
    -0.67
     scrut
    -0.67
    soDeliveryDate
    -0.65
    ivities
    -0.65
     biod
    -0.64
    dos
    -0.64
    POSITIVE LOGITS
     Paste
    0.69
     Till
    0.64
    655
    0.63
     needless
    0.62
     Flavoring
    0.62
     Parenthood
    0.62
     Writ
    0.61
    ound
    0.61
    Sil
    0.60
    PLE
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.