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

    Neuronpedia

    INDEX
    Explanations

    events that are scheduled to take place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scheduled" followed by time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceutical
    -0.75
    soever
    -0.72
    entimes
    -0.68
    alty
    -0.65
    rompt
    -0.60
    Shop
    -0.59
     ported
    -0.58
    Coin
    -0.58
    PI
    -0.58
    Cos
    -0.58
    POSITIVE LOGITS
     eternity
    0.88
    geries
    0.87
     sometime
    0.86
     tomorrow
    0.80
    gery
    0.79
     inclusion
    0.75
     September
    0.72
     August
    0.70
     ages
    0.70
     July
    0.69
    Act Density 0.089%

    No Known Activations