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

    Neuronpedia

    INDEX
    Explanations

    references to violence

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

    words related to physical aggression and conflict

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ocular
    -0.87
    missions
    -0.83
    sonian
    -0.76
    ership
    -0.74
    odes
    -0.74
    ergy
    -0.73
    ramer
    -0.72
    gres
    -0.71
    alty
    -0.71
    ITNESS
    -0.70
    POSITIVE LOGITS
     perpetrated
    1.00
     inflicted
    0.91
     violence
    0.89
     prevention
    0.79
     Violence
    0.78
     suppression
    0.76
    quit
    0.73
    fighting
    0.73
     repression
    0.72
    fully
    0.71
    Act Density 0.026%

    No Known Activations