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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various types of deaths

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inker
    -0.73
    rix
    -0.73
    pan
    -0.72
    Stretch
    -0.71
    ainer
    -0.70
    STEP
    -0.70
    arte
    -0.69
    Parser
    -0.66
     compliment
    -0.64
    PAC
    -0.64
    POSITIVE LOGITS
     deaths
    3.81
     Deaths
    2.77
     fatalities
    2.56
     suicides
    2.22
     death
    2.16
     murders
    2.09
     killings
    2.08
     homicides
    1.98
    death
    1.97
     mortality
    1.82
    Act Density 0.021%

    No Known Activations