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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    选举
    0.77
    起床
    0.73
     férias
    0.73
     regalos
    0.73
     eleições
    0.71
     покупки
    0.71
    开始
    0.68
     chào
    0.68
     всем
    0.68
    但这
    0.68
    POSITIVE LOGITS
     purportedly
    0.75
     presumably
    0.70
    🧠
    0.69
     purported
    0.67
     potentially
    0.67
    presumably
    0.65
     reportedly
    0.64
     collaborator
    0.64
     Apparently
    0.63
    apparently
    0.62
    Act Density 0.000%

    No Known Activations