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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens with formatting specifications from those that denote a function or section within the code or text

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.13
    3:0.06
    4:0.08
    5:0.08
    6:0.10
    7:0.31
    Negative Logits
    EDEFAULT
    -0.39
    AddHtmlAttribute
    -0.34
    PMailer
    -0.33
    værk
    -0.31
    NOPQRST
    -0.31
    TemporalType
    -0.30
    nasio
    -0.30
     متحده
    -0.30
     Gentry
    -0.29
     sauvages
    -0.28
    POSITIVE LOGITS
     onPause
    0.29
     onBackPressed
    0.28
    /*
    0.28
    发表于
    0.27
     onCreateView
    0.27
     initComponents
    0.26
     onStop
    0.26
    Subviews
    0.26
    Sulf
    0.25
    PROM
    0.25
    Act Density 0.003%

    No Known Activations