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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ovember
    -0.84
    enery
    -0.79
    endish
    -0.78
    ervatives
    -0.75
    artney
    -0.75
    borough
    -0.73
    osexual
    -0.73
     Cath
    -0.71
    gypt
    -0.70
    girls
    -0.69
    POSITIVE LOGITS
    Desk
    0.73
    cture
    0.69
    century
    0.67
    QUI
    0.65
     Entered
    0.61
    vantage
    0.59
     inscribed
    0.59
    athered
    0.58
    Zip
    0.58
     BIT
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.