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

    Neuronpedia

    INDEX
    Explanations

    words related to domestic violence

    oai_token-act-pair · gpt-3.5-turbo

    references to domestic violence and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.83
    peror
    -0.80
    */(
    -0.78
    travel
    -0.73
    gob
    -0.73
    source
    -0.71
    Label
    -0.71
    aer
    -0.70
    çĦ
    -0.70
    oyal
    -0.69
    POSITIVE LOGITS
     violence
    0.93
     restraining
    0.89
     prevention
    0.88
     Violence
    0.84
     homicides
    0.84
     suff
    0.81
     abuse
    0.79
     stigma
    0.76
    Viol
    0.76
    violence
    0.76
    Act Density 0.033%

    No Known Activations