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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    geist
    -0.75
    actionDate
    -0.72
    thumbnails
    -0.69
    sed
    -0.69
    inarily
    -0.68
    Sun
    -0.68
    ité
    -0.67
    isol
    -0.66
    swick
    -0.66
    aths
    -0.65
    POSITIVE LOGITS
     STA
    0.68
     mastering
    0.68
     mastered
    0.66
     manuals
    0.65
     Library
    0.64
    usable
    0.63
     feedback
    0.62
     dile
    0.61
     Liberties
    0.59
     Questions
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.