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

    Neuronpedia

    INDEX
    Explanations

    references to victims and victimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.17
    eri
    -0.16
    ark
    -0.16
    é¢ĺ
    -0.16
    azor
    -0.16
    ansom
    -0.15
     (*((
    -0.15
    thing
    -0.15
    ald
    -0.14
    erie
    -0.14
    POSITIVE LOGITS
    hood
    0.23
    /target
    0.17
    peon
    0.16
    olland
    0.16
    ëĭ¹
    0.15
    ology
    0.15
    atically
    0.15
    andalone
    0.14
    spath
    0.14
    inium
    0.14
    Act Density 0.018%

    No Known Activations