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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ɛ
    1.79
    ās
    1.77
     parametrization
    1.76
     artefacts
    1.74
    dataset
    1.71
    ⋯
    1.70
    ām
    1.68
     artefact
    1.67
    äll
    1.66
    ধরনের
    1.66
    POSITIVE LOGITS
     WASHINGTON
    2.17
     Не
    1.74
     .-
    1.72
     -.
    1.72
     FLORIDA
    1.68
     Railroad
    1.66
     То
    1.64
     енер
    1.64
     บ่
    1.64
     Oregon
    1.63
    Act Density 0.039%

    No Known Activations