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

    Neuronpedia

    INDEX
    Explanations

    words related to violent actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocular
    -0.84
    erella
    -0.78
    sonian
    -0.78
    printed
    -0.78
    heit
    -0.75
    STER
    -0.73
    acent
    -0.73
    ļéĨĴ
    -0.72
    artments
    -0.71
    regon
    -0.71
    POSITIVE LOGITS
     violence
    0.92
     retribution
    0.85
     assault
    0.85
     deaths
    0.83
    acre
    0.82
     clashes
    0.81
     jihad
    0.80
     gang
    0.80
     suppression
    0.79
     scenes
    0.79
    Act Density 0.020%

    No Known Activations