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

    Neuronpedia

    INDEX
    Explanations

    references to dosage and comparisons in experimental treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esub
    -0.17
    indle
    -0.15
    ACHI
    -0.14
    mma
    -0.14
    ently
    -0.14
     Maid
    -0.14
    IDAD
    -0.14
    :host
    -0.14
     æ¹
    -0.13
    enta
    -0.13
    POSITIVE LOGITS
     vehicle
    0.38
    vehicle
    0.34
     Vehicle
    0.33
    Vehicle
    0.28
     vehicles
    0.27
     control
    0.25
     Control
    0.24
     Vehicles
    0.23
    control
    0.23
    (vehicle
    0.23
    Act Density 0.005%

    No Known Activations