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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     any
    0.80
     absolutamente
    0.78
     cualquier
    0.75
     qualquer
    0.74
     anything
    0.71
     👀
    0.71
     coolness
    0.70
     absolutely
    0.70
     orice
    0.68
     dinheiro
    0.67
    POSITIVE LOGITS
    dez
    0.63
    6
    0.63
    4
    0.62
    da
    0.61
    Type
    0.59
    3
    0.58
    Примеча
    0.57
    de
    0.57
    uling
    0.57
    Rite
    0.57
    Act Density 0.000%

    No Known Activations