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

    Neuronpedia

    INDEX
    Explanations

    acts of physical violence or aggression

    oai_token-act-pair · gpt-3.5-turbo

    violent actions and physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Balt
    -0.84
    icter
    -0.74
    enment
    -0.72
    soType
    -0.67
    HCR
    -0.67
    stellar
    -0.66
    bh
    -0.66
    edition
    -0.64
    ontent
    -0.64
    DragonMagazine
    -0.63
    POSITIVE LOGITS
     him
    0.81
     bystanders
    0.80
     somebody
    0.80
    gee
    0.77
     someone
    0.77
    ched
    0.72
     holes
    0.69
     pedestrians
    0.68
     anybody
    0.65
     smack
    0.65
    Act Density 0.136%

    No Known Activations