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

    Neuronpedia

    INDEX
    Explanations

    references to utility or helper functions in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Revenir
    -0.52
    PEAT
    -0.51
    nucleus
    -0.50
     Cava
    -0.50
    ایه
    -0.46
     Vorlage
    -0.45
     класс
    -0.45
    keyDown
    -0.45
    Acta
    -0.45
    asiswa
    -0.44
    POSITIVE LOGITS
    basicConfig
    0.87
     <<<<<<<<<<<<<<
    0.85
    util
    0.83
    OGND
    0.82
     kaarangay
    0.76
     <=",
    0.75
     Мексичка
    0.74
    ).</
    0.73
    routeProvider
    0.72
     PartialEq
    0.69
    Act Density 0.001%

    No Known Activations