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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mathemat
    -0.78
     submar
    -0.73
    ebook
    -0.72
     satell
    -0.70
     psychiat
    -0.67
     pir
    -0.67
    artifacts
    -0.66
    awaru
    -0.65
    ulic
    -0.65
    ãĥı
    -0.64
    POSITIVE LOGITS
    -+-+-+-+
    0.71
    addle
    0.71
    gan
    0.71
    leness
    0.64
    rict
    0.63
    matter
    0.62
    core
    0.62
    span
    0.62
     darkest
    0.62
    gans
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.