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

    Neuronpedia

    INDEX
    Explanations

    phrases related to life events or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of life sentences and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.76
    ERC
    -0.71
    ģ«
    -0.71
    Ķ
    -0.71
    yrinth
    -0.71
    uned
    -0.70
    iculty
    -0.70
    ession
    -0.70
     EntityItem
    -0.69
    RECT
    -0.68
    POSITIVE LOGITS
    guards
    1.14
    guard
    1.04
    boats
    0.98
    boat
    0.96
    ously
    0.85
     expectancy
    0.84
    ffen
    0.82
     endangered
    0.79
    tsky
    0.77
    joy
    0.76
    Act Density 0.041%

    No Known Activations