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

    Neuronpedia

    INDEX
    Explanations

    violent actions, especially physical attacks involving punching, hitting, or assaulting

    oai_token-act-pair · gpt-3.5-turbo

    violent actions and related physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spons
    -0.81
    soDeliveryDate
    -0.72
    stellar
    -0.72
    ahime
    -0.71
    DragonMagazine
    -0.70
    TPP
    -0.70
    natureconservancy
    -0.69
    paren
    -0.66
    MSN
    -0.66
     havens
    -0.66
    POSITIVE LOGITS
     bystanders
    0.90
     someone
    0.87
     him
    0.85
     Rodney
    0.85
     Trayvon
    0.82
     unarmed
    0.79
    someone
    0.77
     Kry
    0.76
    ij士
    0.76
     Ronnie
    0.75
    Act Density 0.221%

    No Known Activations