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

    Neuronpedia

    INDEX
    Explanations

    references to actions of killing

    oai_token-act-pair · gpt-3.5-turbo

    uses of the word "kill" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.85
    arity
    -0.72
    gow
    -0.70
     Collider
    -0.67
    fty
    -0.66
    DragonMagazine
    -0.65
    Gi
    -0.65
    Cola
    -0.64
    ARY
    -0.63
    provided
    -0.63
    POSITIVE LOGITS
     spree
    0.94
    joy
    0.84
    switch
    0.78
    mails
    0.77
    killer
    0.75
    houses
    0.73
     killing
    0.73
    blow
    0.72
    req
    0.72
    fish
    0.71
    Act Density 0.045%

    No Known Activations