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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cture
    -0.87
    uin
    -0.82
    ement
    -0.80
    jab
    -0.80
    enary
    -0.73
    bah
    -0.72
    cks
    -0.72
    ascar
    -0.71
    monton
    -0.71
    ertodd
    -0.69
    POSITIVE LOGITS
     incumbent
    0.89
     adherent
    0.74
     contestant
    0.73
     flagship
    0.71
     brightest
    0.68
     drawer
    0.67
     furnished
    0.67
     requisite
    0.66
     commercially
    0.66
     egreg
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.