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

    Neuronpedia

    INDEX
    Explanations

    keywords related to death or fatality

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.70
    Alpha
    -0.68
    PLA
    -0.68
     Plex
    -0.66
     Hilbert
    -0.66
    Stud
    -0.66
    TAG
    -0.65
    arity
    -0.64
     Collider
    -0.63
    orthy
    -0.62
    POSITIVE LOGITS
     deaths
    0.95
    umatic
    0.88
    hooting
    0.84
     Deaths
    0.80
     reckoning
    0.79
    nces
    0.74
    ffen
    0.74
     inquest
    0.73
     overdoses
    0.73
    icides
    0.73
    Act Density 0.014%

    No Known Activations