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

    Neuronpedia

    INDEX
    Explanations

    attends to exponential tokens that are followed by a lower exponent notation

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.24
    2:0.24
    3:0.04
    4:0.07
    5:0.10
    6:0.05
    7:0.08
    Negative Logits
    EndContext
    -0.52
    IndentedString
    -0.45
    存于互联网档案馆
    -0.43
    UrlResolution
    -0.43
    sizeCache
    -0.42
     AssemblyProduct
    -0.42
    ieteur
    -0.41
    GEBURTSDATUM
    -0.41
    colgroup
    -0.39
    RectangleBorder
    -0.39
    POSITIVE LOGITS
     all
    0.28
    else
    0.27
     has
    0.27
     is
    0.26
    uis
    0.24
     eleg
    0.24
    󠁮
    0.23
    has
    0.23
     trabajado
    0.23
     حال
    0.23
    Act Density 0.085%

    No Known Activations