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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific days associated with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckles
    -0.76
     unequ
    -0.71
    onomy
    -0.69
     helicop
    -0.68
     bil
    -0.66
    ahime
    -0.65
    oplan
    -0.65
    err
    -0.64
    utor
    -0.64
    erm
    -0.64
    POSITIVE LOGITS
    aneously
    0.92
     holidays
    0.86
    nings
    0.79
    Reloaded
    0.78
    holiday
    0.75
    BUS
    0.73
    Pope
    0.71
     Thanksgiving
    0.69
    days
    0.68
     Apostle
    0.67
    Act Density 0.043%

    No Known Activations