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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens that denote references or citations from scientific or technical paper markers

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.37
    1:0.28
    2:0.09
    3:0.05
    4:0.05
    5:0.03
    6:0.03
    7:0.06
    Negative Logits
    évaluateur
    -0.43
    󠁿
    -0.36
     Exactos
    -0.32
    TypedDataSet
    -0.31
    脚注の使い方
    -0.30
    RenderAtEndOf
    -0.29
    ьаж
    -0.29
     kaarangay
    -0.29
    AccessorTable
    -0.29
     ErrIntOverflow
    -0.28
    POSITIVE LOGITS
    zty
    0.27
    INCLUDED
    0.27
     tích
    0.26
    WireFormat
    0.26
    FXML
    0.26
    Viited
    0.25
    SuppressLint
    0.25
     nakalista
    0.25
     стаття
    0.24
    ImageIO
    0.24
    Act Density 1.311%

    No Known Activations