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

    Neuronpedia

    INDEX
    Explanations

    mentions of deceased individuals and their surviving relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }{*}{
    -0.52
    $-$
    -0.49
     lenker
    -0.47
    kannya
    -0.47
    gai
    -0.46
    USING
    -0.46
    hafter
    -0.46
     lå
    -0.45
    oga
    -0.45
    $-
    -0.45
    POSITIVE LOGITS
     predeceased
    0.95
     survivors
    0.90
     survived
    0.90
    survi
    0.89
     Survi
    0.86
     mourned
    0.81
    Survivors
    0.79
     Survivors
    0.77
     survivor
    0.74
     surviving
    0.74
    Act Density 0.019%

    No Known Activations