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

    Neuronpedia

    INDEX
    Explanations

    dates written in the month-year format

    oai_token-act-pair · gpt-3.5-turbo

    dates and specific references to years and notable events associated with those dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VPN
    -0.76
    minecraft
    -0.75
    ensical
    -0.72
    GoldMagikarp
    -0.69
    uctor
    -0.69
    soDeliveryDate
    -0.68
    PDATE
    -0.68
    FORMATION
    -0.67
    amental
    -0.67
    ======
    -0.66
    POSITIVE LOGITS
     Ferry
    0.72
     McDonnell
    0.64
    leon
    0.64
    agall
    0.64
     Lau
    0.64
     Nim
    0.63
     gestation
    0.62
     chains
    0.61
     Virus
    0.61
     1918
    0.60
    Act Density 0.376%

    No Known Activations