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

    Neuronpedia

    INDEX
    Explanations

    references to national parks and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.04
    4:0.04
    5:0.04
    6:0.04
    7:0.03
    8:0.03
    9:0.05
    10:0.37
    11:0.21
    Negative Logits
     Crypto
    -1.44
     crypto
    -1.40
     Telegram
    -1.38
    coin
    -1.33
    Bitcoin
    -1.32
     cryptocurrency
    -1.27
     Bitcoin
    -1.27
    Coin
    -1.26
    Bit
    -1.24
    beat
    -1.22
    POSITIVE LOGITS
     Extension
    1.23
     guidelines
    1.23
     Planning
    1.20
     billed
    1.18
     southwest
    1.18
     Policies
    1.17
    ossier
    1.16
     oversees
    1.15
    venants
    1.15
     oversee
    1.15
    Act Density 0.075%

    No Known Activations