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

    Neuronpedia

    INDEX
    Explanations

    references to theft or robbery incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idental
    -0.17
    gewater
    -0.17
    alim
    -0.15
    ury
    -0.15
    Spy
    -0.15
    oto
    -0.15
    errat
    -0.14
    icot
    -0.14
    petto
    -0.14
    TOT
    -0.14
    POSITIVE LOGITS
     té
    0.16
    ANJI
    0.15
    ÑĤик
    0.15
    _PAD
    0.14
    anc
    0.14
     Zucker
    0.14
    rement
    0.13
    ucha
    0.13
     Exploration
    0.13
     osc
    0.13
    Act Density 0.026%

    No Known Activations