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

    Neuronpedia

    INDEX
    Explanations

    sentences containing descriptions of violent or harmful actions inflicted on individuals by others

    oai_token-act-pair · gpt-3.5-turbo

    events involving violence or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.76
     niche
    -0.69
     flexibility
    -0.65
     Jobs
    -0.63
    Planet
    -0.61
    externalActionCode
    -0.61
    PDATED
    -0.61
    Topics
    -0.61
    2019
    -0.59
    iqueness
    -0.59
    POSITIVE LOGITS
     gunfire
    0.87
     invading
    0.79
     onslaught
    0.78
     invaders
    0.78
     encro
    0.77
     barrage
    0.75
    andals
    0.73
     wielding
    0.72
     Arrows
    0.71
    arranted
    0.71
    Act Density 0.568%

    No Known Activations