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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    steen
    -0.83
    apses
    -0.79
    rir
    -0.79
    enter
    -0.78
    ieve
    -0.77
    rs
    -0.73
    umn
    -0.71
    aria
    -0.70
    raq
    -0.70
    apsed
    -0.69
    POSITIVE LOGITS
     poisons
    0.69
     Amph
    0.66
     divergence
    0.64
     Ming
    0.62
     spurious
    0.61
     footh
    0.61
     Kenn
    0.61
     folly
    0.61
     Fisher
    0.61
    atche
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.