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

    Neuronpedia

    INDEX
    Explanations

    attends from specific function-related tokens to specific individual-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.13
    2:0.13
    3:0.12
    4:0.13
    5:0.05
    6:0.13
    7:0.19
    Negative Logits
    bahan
    -0.23
    
    -0.23
    openzeppelin
    -0.23
    庁
    -0.22
    дцать
    -0.22
    ﴿
    -0.22
    writeField
    -0.21
     LoginComponent
    -0.21
    </u>
    -0.20
     Zell
    -0.20
    POSITIVE LOGITS
    Parcelize
    0.33
    ]-'
    0.32
     configureStore
    0.31
    NameInMap
    0.29
    */;
    0.29
    vertebrates
    0.27
    orszá
    0.27
    venirs
    0.27
     sheaves
    0.27
    省市镇
    0.26
    Act Density 0.068%

    No Known Activations