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

    Neuronpedia

    INDEX
    Explanations

    attends to numerical tokens from the citations that follow after those numbers

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.13
    2:0.13
    3:0.08
    4:0.10
    5:0.06
    6:0.12
    7:0.23
    Negative Logits
     وتسجيلات
    -0.29
     Matti
    -0.27
    RTLE
    -0.27
    Hozzáférés
    -0.27
    BagConstraints
    -0.27
     Pyrénées
    -0.27
    breadcrumbs
    -0.27
     AssemblyTitle
    -0.27
    annulation
    -0.27
    <()>
    -0.27
    POSITIVE LOGITS
    +#+#
    0.36
    ँच
    0.29
    joba
    0.27
    soort
    0.26
     htons
    0.25
    ofType
    0.25
    хьтан
    0.24
    轭
    0.24
    hloromethane
    0.24
    цездатний
    0.24
    Act Density 1.879%

    No Known Activations