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

    Neuronpedia

    INDEX
    Explanations

    references to physical violence and assault

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical violence and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemImage
    -0.71
    iterranean
    -0.67
    ":["
    -0.65
    Balt
    -0.65
    Sense
    -0.64
    ventures
    -0.64
    DCS
    -0.62
    DragonMagazine
    -0.62
     ausp
    -0.61
    ACTION
    -0.61
    POSITIVE LOGITS
     senseless
    1.28
     unconscious
    1.04
     merciless
    1.03
     violently
    0.97
    selves
    0.95
     brutally
    0.86
    self
    0.85
     severely
    0.84
     relentlessly
    0.82
     repeatedly
    0.80
    Act Density 0.195%

    No Known Activations