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

    Neuronpedia

    INDEX
    Explanations

    dates, days of the week, and years

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deserted
    -0.67
    igham
    -0.66
     distance
    -0.61
    andestine
    -0.60
     domest
    -0.60
    illas
    -0.57
     conqu
    -0.56
     distances
    -0.55
     extinct
    -0.55
     turbulence
    -0.54
    POSITIVE LOGITS
    th
    0.77
    externalActionCode
    0.65
    thouse
    0.64
    stice
    0.63
    JV
    0.63
    NPR
    0.62
    Switch
    0.62
    bilt
    0.62
     partName
    0.61
    ember
    0.59
    Act Density 0.107%

    No Known Activations