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

    Neuronpedia

    INDEX
    Explanations

    references to violent actions or crimes involving death

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.82
    wcsstore
    -0.73
    Cola
    -0.70
     Collider
    -0.70
    Scot
    -0.70
    por
    -0.67
     Bubble
    -0.65
    cession
    -0.64
    oday
    -0.64
    ertain
    -0.63
    POSITIVE LOGITS
     spree
    1.05
    switch
    0.88
    mails
    0.87
     rampage
    0.87
    joy
    0.83
     innocent
    0.82
     civilians
    0.82
     murderer
    0.81
     murdering
    0.81
     slain
    0.79
    Act Density 0.628%

    No Known Activations