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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kandungan
    0.57
    Hepin
    0.53
    䡇
    0.52
    攽
    0.52
     autumnal
    0.52
     échanc
    0.51
     這個
    0.50
     aliments
    0.50
    ंगाई
    0.50
     బ్రిటిషు
    0.49
    POSITIVE LOGITS
     a
    0.96
    2
    0.82
    1
    0.79
     the
    0.75
    3
    0.69
    4
    0.68
    6
    0.67
    7
    0.66
     an
    0.66
    5
    0.64
    Act Density 3.298%

    No Known Activations