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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reckoned
    -0.73
    BuyableInstoreAndOnline
    -0.72
     Tot
    -0.70
    uality
    -0.70
    ãĥĺ
    -0.69
    nor
    -0.68
    ITED
    -0.68
    Pg
    -0.68
    UME
    -0.67
    eros
    -0.67
    POSITIVE LOGITS
    league
    0.65
     abrupt
    0.63
    magic
    0.63
    ertodd
    0.61
    rence
    0.61
     disillusion
    0.61
     reorgan
    0.60
    arya
    0.59
     associates
    0.58
    iren
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.