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

    Neuronpedia

    INDEX
    Explanations

    instances of impactful or pivotal moments in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.14
    4:0.23
    5:0.05
    6:0.05
    7:0.14
    8:0.06
    9:0.03
    10:0.05
    11:0.08
    Negative Logits
     schemes
    -2.47
     viruses
    -2.31
    acons
    -2.21
     discour
    -2.08
    ificial
    -2.02
     mechanisms
    -1.97
     calibr
    -1.97
     incentiv
    -1.97
    olesc
    -1.96
     Enh
    -1.94
    POSITIVE LOGITS
     Originally
    2.62
     ⓘ
    2.35
    his
    2.35
     Written
    2.18
     Woodward
    2.17
    Shortly
    2.16
     Reed
    2.15
     Booker
    2.14
     +++
    2.14
    inventoryQuantity
    2.13
    Act Density 0.801%

    No Known Activations