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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to self-reference and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VOID
    -0.16
     Oc
    -0.14
    ı
    -0.14
    ertest
    -0.14
    ŀ
    -0.14
    डर
    -0.14
    637
    -0.14
     Rob
    -0.14
     Bord
    -0.14
    ">ÃĹ</
    -0.14
    POSITIVE LOGITS
    ignet
    0.16
     Truy
    0.15
    refresh
    0.15
    azen
    0.15
    .getResult
    0.14
    elon
    0.14
    irement
    0.14
    mpeg
    0.14
    ingo
    0.14
    uron
    0.14
    Act Density 0.002%

    No Known Activations