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

    Neuronpedia

    INDEX
    Explanations

    instances of interactions between variables in a study

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.71
     colorés
    -0.62
    وأضاف
    -0.60
     ویکی‌پدیای
    -0.59
     ujednoznacz
    -0.58
     mobilité
    -0.57
     CALIF
    -0.55
    спонд
    -0.55
     bén
    -0.55
     rémun
    -0.55
    POSITIVE LOGITS
     Wikimedijinoj
    0.52
     traps
    0.52
    devServer
    0.50
    atko
    0.49
     collabor
    0.48
    การ
    0.48
    ത്തി
    0.48
    TERNS
    0.48
     calls
    0.47
     <=",
    0.47
    Act Density 0.004%

    No Known Activations