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

    Neuronpedia

    INDEX
    Explanations

    references to receiving or giving gifts and expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    elements related to holiday gifting and surprises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     choke
    -0.81
     manoeuv
    -0.80
     kilomet
    -0.79
    ewitness
    -0.77
     constituencies
    -0.76
     veh
    -0.76
     insurgency
    -0.75
     sectarian
    -0.72
    iferation
    -0.72
     simulator
    -0.72
    POSITIVE LOGITS
     THANK
    1.05
    etsy
    1.01
     Gifts
    0.96
    Santa
    0.90
     adorable
    0.89
     generosity
    0.88
     gift
    0.86
     Delicious
    0.86
     christ
    0.85
     gifts
    0.83
    Act Density 0.202%

    No Known Activations