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

    Neuronpedia

    INDEX
    Explanations

    occurrences of individuals being found in various states or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals being found or discovered, often in critical or alarming situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.76
    adan
    -0.73
    !/
    -0.73
    ichever
    -0.69
    creation
    -0.67
    Times
    -0.65
    uries
    -0.65
    é¾įå¥ij士
    -0.64
    ilee
    -0.64
    rients
    -0.63
    POSITIVE LOGITS
     lying
    1.07
     hiding
    1.06
     slumped
    1.02
     lifeless
    1.02
     missing
    0.97
     dangling
    0.95
     lurking
    0.94
     dead
    0.93
    susp
    0.93
     charred
    0.92
    Act Density 0.220%

    No Known Activations