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

    Neuronpedia

    INDEX
    Explanations

    terms associated with equipment or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ents
    -0.17
    kul
    -0.17
    ertia
    -0.16
    appers
    -0.15
    elsey
    -0.15
    dale
    -0.14
    ever
    -0.14
    mars
    -0.14
    icare
    -0.14
    ency
    -0.14
    POSITIVE LOGITS
    shift
    0.22
    boxes
    0.20
    hart
    0.17
    box
    0.17
    _inches
    0.17
    ãģ¹ãģį
    0.16
    beit
    0.16
    SHIFT
    0.16
    former
    0.15
    nger
    0.15
    Act Density 0.011%

    No Known Activations