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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities with military or leadership titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etwork
    -0.15
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.15
    ATERIAL
    -0.14
     drawn
    -0.14
     spread
    -0.14
    hani
    -0.14
    unar
    -0.14
    ÑĢок
    -0.13
    Archive
    -0.13
    åľ°æĸ¹
    -0.13
    POSITIVE LOGITS
    478
    0.16
    елик
    0.15
    bedo
    0.15
    سÙĪ
    0.14
    deo
    0.14
    ladu
    0.14
    iaz
    0.14
    ovu
    0.14
     rut
    0.14
    struments
    0.14
    Act Density 0.015%

    No Known Activations