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

    Neuronpedia

    INDEX
    Explanations

    references to domestic violence and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.16
    irus
    -0.16
    herit
    -0.16
     guid
    -0.15
     nat
    -0.15
    arkin
    -0.15
     prism
    -0.15
    ansom
    -0.14
    remen
    -0.14
    ZD
    -0.14
    POSITIVE LOGITS
     Domestic
    0.32
     domestic
    0.30
     Violence
    0.28
     violence
    0.27
    /dom
    0.25
    Dom
    0.25
    .Dom
    0.24
     batter
    0.23
     domest
    0.22
     IPV
    0.22
    Act Density 0.063%

    No Known Activations