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

    Neuronpedia

    INDEX
    Explanations

    keywords related to crimes, particularly homicide

    oai_token-act-pair · gpt-3.5-turbo

    references to homicide statistics and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ais
    -0.88
    amina
    -0.84
    Cola
    -0.78
    arte
    -0.73
    kef
    -0.71
    oyal
    -0.70
    ebus
    -0.70
    enna
    -0.69
    eem
    -0.69
    endon
    -0.68
    POSITIVE LOGITS
     homicide
    1.14
     homicides
    1.00
     spree
    0.90
     murders
    0.74
     deaths
    0.74
     victim
    0.73
     killings
    0.72
    icide
    0.72
     slaying
    0.70
     shootings
    0.70
    Act Density 0.018%

    No Known Activations