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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal experience and recommendations regarding products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugas
    -0.15
    çĵľ
    -0.13
    uncios
    -0.13
    ãĤ¤ãĥĪ
    -0.13
    asje
    -0.13
    straction
    -0.13
     Svens
    -0.13
    arken
    -0.12
    vae
    -0.12
    krv
    -0.12
    POSITIVE LOGITS
     order
    1.06
     orders
    0.97
    order
    0.92
    -order
    0.90
     ordering
    0.90
     Order
    0.89
     ordered
    0.88
    Order
    0.85
     ORDER
    0.84
     Orders
    0.81
    Act Density 0.032%

    No Known Activations