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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isine
    -0.73
     leveled
    -0.61
    mens
    -0.61
     countered
    -0.59
    anni
    -0.57
     (~
    -0.57
     tremend
    -0.56
    ework
    -0.56
     pant
    -0.56
     shr
    -0.55
    POSITIVE LOGITS
    Reports
    0.73
    Bloomberg
    0.70
    é¾į
    0.69
     bilateral
    0.67
    £ı
    0.66
     Advocate
    0.66
    DonaldTrump
    0.66
    APH
    0.65
    20439
    0.64
    APTER
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.