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

    Neuronpedia

    INDEX
    Explanations

    references to discrete mathematical concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ؤية
    -0.71
     LOGGER
    -0.70
    tableWidget
    -0.69
     Bowers
    -0.68
     poliester
    -0.66
    JSP
    -0.65
     Beverly
    -0.63
    }?>
    -0.62
    Beverly
    -0.60
    Nadia
    -0.60
    POSITIVE LOGITS
    discrete
    1.34
     discrete
    1.31
     Discrete
    1.27
    Discrete
    1.22
     discreet
    0.91
    discre
    0.89
     Discre
    0.88
    CRETE
    0.82
     discre
    0.80
    Discre
    0.80
    Act Density 0.011%

    No Known Activations