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

    Neuronpedia

    INDEX
    Explanations

    references to obligation or necessity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     censiti
    -0.74
     EconPapers
    -0.61
    Посилання
    -0.61
    :✨
    -0.60
     محفوظة
    -0.60
     समीक्षाओं
    -0.60
     NSCoder
    -0.59
    таратура
    -0.59
     Ejemplo
    -0.58
    vece
    -0.57
    POSITIVE LOGITS
    Somewhere
    0.74
     somewhere
    0.72
    somewhere
    0.71
     inevitable
    0.71
     inevitably
    0.70
    必ず
    0.68
    Somebody
    0.68
     Somewhere
    0.66
     SOMETHING
    0.65
    Someone
    0.63
    Act Density 0.240%

    No Known Activations