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

    Neuronpedia

    INDEX
    Explanations

    instances of violent actions such as shootings, attacks, stabbings, and bombings

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennial
    -0.84
     aster
    -0.78
    ripp
    -0.73
    cancer
    -0.69
    ãĤ´ãĥ³
    -0.69
     ç¥ŀ
    -0.68
    onyms
    -0.66
    alog
    -0.65
    ANN
    -0.64
    eric
    -0.64
    POSITIVE LOGITS
     unarmed
    0.91
     parked
    0.91
     bystanders
    0.86
     fleeing
    0.85
     bystand
    0.82
     attempting
    0.79
     parach
    0.79
     bicy
    0.79
     sleeping
    0.73
     suspected
    0.72
    Act Density 0.434%

    No Known Activations