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

    Neuronpedia

    INDEX
    Explanations

    references to marital status and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wards
    -0.17
    /response
    -0.15
    ÙĦÛĮت
    -0.15
    egin
    -0.15
    ener
    -0.15
    ador
    -0.14
    íĮĶ
    -0.14
    BJECT
    -0.14
    luž
    -0.14
    Æ¡n
    -0.14
    POSITIVE LOGITS
     vows
    0.16
    itere
    0.15
    /div
    0.15
     couples
    0.15
    maids
    0.15
    arkin
    0.14
     Gri
    0.14
    519
    0.14
    /lic
    0.14
     Troll
    0.14
    Act Density 0.069%

    No Known Activations