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

    Neuronpedia

    INDEX
    Explanations

    words related to mass events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to mass violence events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.84
    thens
    -0.67
    66666666
    -0.65
    thy
    -0.64
    thritis
    -0.63
     Ital
    -0.63
    mingham
    -0.61
    sbm
    -0.61
    yssey
    -0.60
    chy
    -0.60
    POSITIVE LOGITS
    achusetts
    1.26
     incarceration
    0.76
    achus
    0.73
     mass
    0.73
     quantities
    0.71
     transit
    0.71
     exodus
    0.71
     spect
    0.69
    ographically
    0.69
     transportation
    0.68
    Act Density 0.011%

    No Known Activations