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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent actions and executions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    diali
    -0.47
     laude
    -0.46
    Capricorn
    -0.44
     hosting
    -0.42
    ITED
    -0.42
     않
    -0.41
    WithIOException
    -0.41
     متعلقه
    -0.41
     ild
    -0.40
    wość
    -0.40
    POSITIVE LOGITS
     death
    1.21
     deaths
    1.08
    death
    1.05
     DEATH
    0.96
     posthum
    0.92
     Death
    0.91
     mortality
    0.91
     killing
    0.91
     Deaths
    0.90
     suicide
    0.89
    Act Density 0.600%

    No Known Activations