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

    Neuronpedia

    INDEX
    Explanations

    attends to reserved fields from subsequent tokens or code structures

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.12
    2:0.12
    3:0.14
    4:0.12
    5:0.08
    6:0.12
    7:0.16
    Negative Logits
    oa̍t
    -0.34
    AndEndTag
    -0.30
    Ệ
    -0.29
     CardView
    -0.29
     }{@
    -0.28
    Literat
    -0.28
     onPage
    -0.26
    TemporalType
    -0.26
     Bue
    -0.26
     routes
    -0.26
    POSITIVE LOGITS
    ConstraintMaker
    0.40
    makeConstraints
    0.33
    RenderAtEndOf
    0.32
    antMatchers
    0.32
    UserScript
    0.32
    談社
    0.31
     '\\;'
    0.31
     arşivlendi
    0.30
    abank
    0.28
    SequentialGroup
    0.27
    Act Density 0.011%

    No Known Activations