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

    Neuronpedia

    INDEX
    Explanations

    references to acts of violence involving stabbing

    oai_token-act-pair · gpt-3.5-turbo

    references to stabbing incidents and related violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.81
    tz
    -0.72
     Leban
    -0.71
     Organization
    -0.70
    quickShipAvailable
    -0.70
    oS
    -0.69
    ais
    -0.65
     Geographic
    -0.65
    XM
    -0.64
    AMA
    -0.64
    POSITIVE LOGITS
    lished
    0.97
     wounds
    0.93
     slit
    0.85
     stabbing
    0.84
     stabbed
    0.83
    lihood
    0.82
     spree
    0.80
     stab
    0.79
     rampage
    0.79
     wrists
    0.77
    Act Density 0.023%

    No Known Activations