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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tics
    -0.69
    Constructed
    -0.65
     Bound
    -0.65
    Rail
    -0.61
    displayText
    -0.61
    zar
    -0.60
    craft
    -0.59
    arc
    -0.58
    tra
    -0.58
    ceans
    -0.58
    POSITIVE LOGITS
     proport
    0.81
    ĸļ
    0.79
     veter
    0.76
    reditary
    0.73
    Ń·
    0.71
     mathemat
    0.71
     unden
    0.70
     precedence
    0.70
     smokes
    0.68
    udo
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.