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

    Neuronpedia

    INDEX
    Explanations

    programming-related parameters and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enda
    -0.16
    pressions
    -0.16
    piration
    -0.15
    okoj
    -0.14
    ifact
    -0.14
    orges
    -0.14
    oning
    -0.14
    ucket
    -0.14
    zej
    -0.14
    ddit
    -0.13
    POSITIVE LOGITS
    land
    0.16
    )init
    0.16
    inkel
    0.14
    ëĭĪëĭ¤
    0.14
    stalk
    0.14
    sock
    0.13
    alth
    0.13
    ëįķ
    0.13
    init
    0.13
    loc
    0.13
    Act Density 0.032%

    No Known Activations