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

    Neuronpedia

    INDEX
    Explanations

    references to identifying and handling the deceased

    oai_token-act-pair · gpt-3.5-turbo

    references to deceased individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.84
    inka
    -0.75
    kef
    -0.75
    erity
    -0.73
    orers
    -0.68
     Wilkinson
    -0.67
    ifling
    -0.67
    Ag
    -0.66
    dp
    -0.66
    Roy
    -0.66
    POSITIVE LOGITS
     deceased
    1.18
     DEAD
    0.84
     corpse
    0.84
     carc
    0.72
     widow
    0.69
     toll
    0.68
     souls
    0.67
    soever
    0.67
     corpses
    0.66
     soul
    0.66
    Act Density 0.016%

    No Known Activations