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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to death and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    removeClass
    -0.46
    <bos>
    -0.44
    setResizable
    -0.43
    ueta
    -0.42
    buzo
    -0.41
    Ặ
    -0.41
     rega
    -0.41
    ulkan
    -0.41
    Tahoma
    -0.41
    parseDouble
    -0.41
    POSITIVE LOGITS
     death
    1.39
     deaths
    1.35
    death
    1.16
     DEATH
    1.13
     killed
    1.12
     died
    1.10
     Death
    1.08
    Death
    1.07
     décédé
    1.07
     Deaths
    1.06
    Act Density 0.391%

    No Known Activations