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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     syndrome
    -0.73
    kind
    -0.64
    mith
    -0.61
    les
    -0.59
    mare
    -0.58
    lement
    -0.57
    mas
    -0.56
     Syndrome
    -0.56
     Cowboys
    -0.55
     Indust
    -0.55
    POSITIVE LOGITS
    ftime
    0.77
    cipled
    0.73
    essor
    0.72
    ipal
    0.72
    uci
    0.72
    osure
    0.71
    ãĤĬ
    0.71
    姫
    0.70
    encer
    0.70
    chrome
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.