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

    Neuronpedia

    INDEX
    Explanations

    references to written documents or formal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.88
    principalTable
    -0.65
     lenker
    -0.65
    devamını
    -0.64
    -0.64
    tagHelperRunner
    -0.63
    PYX
    -0.62
     Signalez
    -0.62
    ędzy
    -0.62
    KommentareTeilen
    -0.61
    POSITIVE LOGITS
     written
    2.81
     Written
    2.40
    Written
    2.24
    written
    2.20
     WRITTEN
    2.15
     escrito
    1.56
     printed
    1.40
     écrite
    1.37
     tertulis
    1.33
     escritas
    1.32
    Act Density 0.127%

    No Known Activations