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

    Neuronpedia

    INDEX
    Explanations

    attends to data type names from preceding related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.10
    2:0.12
    3:0.10
    4:0.17
    5:0.18
    6:0.07
    7:0.10
    Negative Logits
     Paglinawan
    -0.32
     Rady
    -0.28
    WireFormatLite
    -0.26
     informée
    -0.24
    apol
    -0.24
     rege
    -0.23
    StoryboardSegue
    -0.23
    XmlType
    -0.23
     Kommission
    -0.23
     CommonModule
    -0.22
    POSITIVE LOGITS
    ISupport
    0.33
     intptr
    0.32
    ContentAsync
    0.32
     sessionFactory
    0.32
    ContentValues
    0.30
    脚注の使い方
    0.30
    帖最后由
    0.29
    CLUYE
    0.28
    niająca
    0.28
    msgSender
    0.28
    Act Density 0.079%

    No Known Activations