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

    Neuronpedia

    INDEX
    Explanations

    references to family and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adm
    -0.17
    ruz
    -0.15
     Cabinet
    -0.15
     åĸ
    -0.15
    roz
    -0.14
     Empire
    -0.14
     Moor
    -0.14
     Moz
    -0.14
    andon
    -0.14
     Loud
    -0.14
    POSITIVE LOGITS
    kili
    0.17
    ussen
    0.15
    anean
    0.15
     iddi
    0.14
    itical
    0.14
    curacy
    0.14
    ulur
    0.14
    dech
    0.14
    _DLL
    0.14
    anut
    0.14
    Act Density 0.229%

    No Known Activations