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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and their formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ároz
    -0.68
     ویکی‌پدیای
    -0.66
     Naf
    -0.64
    úrese
    -0.61
    RectangleBorder
    -0.59
    canza
    -0.59
    iſt
    -0.58
     entanto
    -0.56
    $.
    -0.55
    hésite
    -0.55
    POSITIVE LOGITS
    __()
    0.83
    rrbracket
    0.82
    rfloor
    0.81
    】
    0.77
    ագրություններ
    0.77
    enderror
    0.75
    endcsname
    0.73
    Demografie
    0.72
    .*")]
    0.72
     kasarigan
    0.72
    Act Density 1.785%

    No Known Activations