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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' ages

    oai_token-act-pair · gpt-3.5-turbo

    numerical age values associated with people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berus
    -0.60
     Replay
    -0.54
     clos
    -0.54
    cru
    -0.51
    among
    -0.51
     lows
    -0.51
     incidental
    -0.51
    .):
    -0.50
     appro
    -0.49
    drawn
    -0.49
    POSITIVE LOGITS
     year
    1.28
    year
    1.15
    -
    1.04
     yr
    1.01
     Year
    0.93
    yr
    0.92
    Year
    0.90
     month
    0.85
    -[
    0.81
    something
    0.81
    Act Density 0.077%

    No Known Activations