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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or conditions in a legal context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.89
    Попис
    -0.83
    expandindo
    -0.78
    Rptr
    -0.77
    İstinadlar
    -0.74
    Referencies
    -0.73
    pewa
    -0.73
     Euripides
    -0.73
    PreferredItem
    -0.72
     мәкал
    -0.72
    POSITIVE LOGITS
     which
    0.97
     wherein
    0.69
    which
    0.69
     where
    0.66
     whose
    0.62
     WHICH
    0.61
     why
    0.59
     whereby
    0.57
     chez
    0.56
     torno
    0.56
    Act Density 0.048%

    No Known Activations