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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens marked with numerical identifiers from tokens marked with square brackets

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.12
    2:0.09
    3:0.06
    4:0.06
    5:0.06
    6:0.08
    7:0.40
    Negative Logits
    +#+#
    -0.44
    InjectAttribute
    -0.43
     الحره
    -0.35
    ScopeManager
    -0.35
    ReusableCell
    -0.34
     متعلقه
    -0.33
     Wiktionnaire
    -0.33
     समीक्षाओं
    -0.32
     Wicidata
    -0.32
     BoxFit
    -0.32
    POSITIVE LOGITS
     exclu
    0.21
    Superclass
    0.21
     Groß
    0.21
    ConverterFactory
    0.21
    MÁS
    0.21
     Einfach
    0.21
    iento
    0.20
    боль
    0.20
     dum
    0.20
     Heaven
    0.19
    Act Density 0.018%

    No Known Activations