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

    Neuronpedia

    INDEX
    Explanations

    references to mortality and the consequences of death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.46
     transfieras
    -0.33
    viders
    -0.31
    ñales
    -0.31
    omod
    -0.31
     Chwiliwch
    -0.30
    rzost
    -0.29
     незавершена
    -0.29
     trấn
    -0.29
    vertre
    -0.29
    POSITIVE LOGITS
     death
    3.11
     died
    2.86
     deaths
    2.80
    death
    2.67
     dead
    2.64
     dying
    2.59
     Death
    2.58
    Death
    2.53
     DEATH
    2.52
    dead
    2.30
    Act Density 2.143%

    No Known Activations