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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different forms of violence, specifically domestic violence

    oai_token-act-pair · gpt-3.5-turbo

    references to domestic violence and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.86
    Flag
    -0.80
    hart
    -0.78
    UMP
    -0.75
    isse
    -0.73
    jon
    -0.71
    Recipe
    -0.70
    DIT
    -0.69
    mand
    -0.69
    ISSION
    -0.68
    POSITIVE LOGITS
     violence
    1.06
     abuse
    0.97
     prevention
    0.91
     abusers
    0.89
     homicides
    0.87
     Violence
    0.86
     offenders
    0.85
     gangs
    0.83
    abuse
    0.82
     homelessness
    0.81
    Act Density 0.018%

    No Known Activations