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

    Neuronpedia

    INDEX
    Explanations

    references to doors and their associated actions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vrier
    -0.17
    tl
    -0.17
    adele
    -0.16
    tu
    -0.16
    tank
    -0.16
    dic
    -0.15
    tlement
    -0.15
    ertools
    -0.15
    OfWork
    -0.15
    edd
    -0.15
    POSITIVE LOGITS
    ways
    0.45
    bell
    0.40
    frame
    0.32
    keeper
    0.29
    steps
    0.28
    /window
    0.26
    frames
    0.26
    WAYS
    0.26
    step
    0.25
     knob
    0.25
    Act Density 0.042%

    No Known Activations