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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nào
    -0.08
     gi
    -0.07
     id
    -0.07
     x
    -0.07
     Ann
    -0.07
    首要
    -0.06
     wind
    -0.06
     sch
    -0.06
     Heller
    -0.06
    項
    -0.06
    POSITIVE LOGITS
    utherford
    0.07
    fila
    0.07
     POR
    0.07
    ❴
    0.07
    Marca
    0.07
    固定的
    0.07
    粗
    0.07
     ושל
    0.07
     работу
    0.07
     underwear
    0.07
    Act Density 0.003%

    No Known Activations