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

    Neuronpedia

    INDEX
    Explanations

    terms related to violent events, such as shootings and wars

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.70
    ĪĴ
    -0.69
    thens
    -0.69
    ilk
    -0.69
    stal
    -0.68
    shire
    -0.67
    yssey
    -0.67
    BILITIES
    -0.67
    nos
    -0.66
    tis
    -0.65
    POSITIVE LOGITS
    achusetts
    1.48
    achus
    1.06
    imil
    0.86
    acre
    0.85
    achu
    0.82
     transit
    0.79
    aging
    0.79
     exodus
    0.78
    eval
    0.77
    ages
    0.77
    Act Density 0.671%

    No Known Activations