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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enthusi
    -0.82
    ramid
    -0.78
    redd
    -0.74
     treadmill
    -0.73
    orth
    -0.73
    Pers
    -0.71
    aic
    -0.67
     millenn
    -0.64
    aths
    -0.63
    hester
    -0.63
    POSITIVE LOGITS
    clusive
    0.72
    igate
    0.70
    stack
    0.66
    packages
    0.66
    semble
    0.65
    uki
    0.64
    nets
    0.62
    itionally
    0.62
     Scorp
    0.60
    ulu
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.