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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     surprisingly
    0.86
    idemargin
    0.73
     dashed
    0.68
     excreted
    0.67
     sometimes
    0.67
    បាន
    0.67
     attenuate
    0.66
     monotonically
    0.66
     intravenously
    0.66
     orthogonal
    0.65
    POSITIVE LOGITS
    es
    1.01
     noticias
    0.84
     Advice
    0.79
     الاولى
    0.75
    ાર્થ
    0.74
    ن
    0.74
    Restaurant
    0.72
     પ્રથમ
    0.71
    小编
    0.71
    娲
    0.71
    Act Density 0.002%

    No Known Activations