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

    Neuronpedia

    INDEX
    Explanations

    mentions of violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to various forms and contexts of violence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ocular
    -0.84
    missions
    -0.84
    ramer
    -0.77
    odes
    -0.76
    sonian
    -0.76
    ergy
    -0.74
    gres
    -0.74
    arton
    -0.74
    dit
    -0.72
    ership
    -0.71
    POSITIVE LOGITS
     perpetrated
    1.01
     violence
    0.93
     inflicted
    0.91
     suppression
    0.82
     Violence
    0.78
     repression
    0.77
    quit
    0.74
     prevention
    0.73
     oppression
    0.72
     spree
    0.71
    Act Density 0.023%

    No Known Activations