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

    Neuronpedia

    INDEX
    Explanations

    references to scientific papers or studies, particularly denoted by citation formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.67
     ویکی‌آمباردا
    -0.63
     gradi
    -0.56
    ########.
    -0.56
     famí
    -0.54
    laim
    -0.54
    cheid
    -0.54
    suits
    -0.54
    llary
    -0.53
     متعلقه
    -0.53
    POSITIVE LOGITS
    pone
    1.17
    PONE
    0.96
     pone
    0.75
     resourceCulture
    0.74
    arXiv
    0.68
    openzeppelin
    0.62
     Pony
    0.61
    bootstrapcdn
    0.60
     planches
    0.59
     PLOS
    0.59
    Act Density 0.255%

    No Known Activations