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

    Neuronpedia

    INDEX
    Explanations

    timestamps indicating time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal markers or time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okers
    -0.60
    ARDS
    -0.58
    adle
    -0.58
    entials
    -0.57
    boro
    -0.55
    ordes
    -0.54
    nyder
    -0.54
    onto
    -0.53
    angan
    -0.52
    que
    -0.52
    POSITIVE LOGITS
     month
    1.10
     week
    1.06
     year
    1.03
     Updated
    0.98
     ditch
    0.94
     night
    0.92
     updated
    0.88
     rites
    0.85
    ingly
    0.83
     October
    0.82
    Act Density 0.042%

    No Known Activations