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

    Neuronpedia

    INDEX
    Explanations

    references to gear and equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ents
    -0.17
    elsey
    -0.17
    ency
    -0.16
    dale
    -0.16
    ertia
    -0.16
    enties
    -0.15
    eshire
    -0.15
    mars
    -0.15
    elon
    -0.15
    ège
    -0.15
    POSITIVE LOGITS
    shift
    0.28
    boxes
    0.23
    hart
    0.20
    box
    0.19
    wheel
    0.18
    SHIFT
    0.18
    _inches
    0.18
    beit
    0.18
    head
    0.17
     shift
    0.17
    Act Density 0.009%

    No Known Activations