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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal acts involving harm or death to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to murders and killings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -1.03
    por
    -0.78
     reimb
    -0.77
    catentry
    -0.76
    dding
    -0.74
    iasm
    -0.74
    ocating
    -0.69
    direction
    -0.69
    wcsstore
    -0.69
    à¼
    -0.67
    POSITIVE LOGITS
     unarmed
    1.14
     innoc
    1.06
     innocent
    1.03
     Trayvon
    1.01
     Cecil
    0.94
     Osama
    0.92
     unborn
    0.90
     Freddie
    0.88
     168
    0.88
     hostages
    0.86
    Act Density 0.141%

    No Known Activations