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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ก
    0.52
    [
    0.52
    that
    0.47
    á
    0.45
    Confidence
    0.44
    raped
    0.44
    encoding
    0.44
    iping
    0.43
    *
    0.41
    ast
    0.41
    POSITIVE LOGITS
    וּ
    0.52
     toilet
    0.49
     unor
    0.49
     thoughtfulness
    0.48
    וֹ
    0.47
     unele
    0.47
     Toilet
    0.46
     প্রতিহিংস
    0.46
    ڈین
    0.46
     emocion
    0.46
    Act Density 0.000%

    No Known Activations