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

    Neuronpedia

    INDEX
    Explanations

    references to dead bodies or decaying corpses

    oai_token-act-pair · gpt-3.5-turbo

    references to corpses and death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.91
    ĨĴ
    -0.68
    Americ
    -0.66
    itudes
    -0.66
    ellig
    -0.65
    iasm
    -0.64
     nort
    -0.63
     Berks
    -0.63
    ipolar
    -0.63
    orus
    -0.63
    POSITIVE LOGITS
     carc
    1.13
     Corpse
    1.12
     corpses
    1.09
     corpse
    1.04
    bage
    0.83
     slain
    0.79
    letal
    0.77
     inciner
    0.74
     crem
    0.74
     rotting
    0.73
    Act Density 0.037%

    No Known Activations