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

    Neuronpedia

    INDEX
    Explanations

    attends to the token "helpers" from programming-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.12
    2:0.12
    3:0.12
    4:0.12
    5:0.05
    6:0.20
    7:0.16
    Negative Logits
     typelib
    -0.42
    ftagPool
    -0.38
    bibfield
    -0.36
    queryInterface
    -0.35
    bibinfo
    -0.33
     resourceCulture
    -0.32
     GenerationType
    -0.32
    ]='\
    -0.31
    WebVitals
    -0.31
    ConstraintMaker
    -0.29
    POSITIVE LOGITS
    Hochspringen
    0.38
     đỉnh
    0.32
    ierta
    0.31
    Bronnen
    0.31
    apen
    0.27
    EditorBrowsable
    0.27
    fitriones
    0.27
     ailleurs
    0.26
    是一
    0.26
    سل
    0.26
    Act Density 0.081%

    No Known Activations