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

    Neuronpedia

    INDEX
    Explanations

    attends to digit tokens from their corresponding bracketed numerical tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.19
    2:0.11
    3:0.08
    4:0.15
    5:0.15
    6:0.05
    7:0.12
    Negative Logits
     telefónica
    -0.31
    ✭✭
    -0.28
    <?
    -0.27
    ană
    -0.27
    mipmap
    -0.27
    PANY
    -0.27
    ESOME
    -0.26
    værk
    -0.25
     "..\..\
    -0.25
    ngdoc
    -0.24
    POSITIVE LOGITS
    InputBorder
    0.36
     ComVisible
    0.33
     שוליים
    0.31
     समीक्षाओं
    0.31
    getDoctrine
    0.29
    ReusableCell
    0.28
    abetes
    0.27
    BagLayout
    0.27
    ViewImports
    0.26
    vokat
    0.26
    Act Density 0.614%

    No Known Activations