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

    Neuronpedia

    INDEX
    Explanations

    attends to numeric tokens representing measurements from numerical values in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.15
    2:0.13
    3:0.13
    4:0.11
    5:0.08
    6:0.06
    7:0.18
    Negative Logits
    EClass
    -0.34
    ])));
    -0.34
     Symphon
    -0.33
     Mollus
    -0.32
    OrBuilder
    -0.32
    +#+#
    -0.32
    NameInMap
    -0.31
    potranspiration
    -0.31
    CloseOperation
    -0.29
    $.
    -0.29
    POSITIVE LOGITS
     متعلقه
    0.36
     فريبيس
    0.32
    NUMX
    0.28
    formik
    0.28
    ktop
    0.27
     schrift
    0.27
    handlung
    0.26
    isional
    0.26
    portál
    0.26
     inge
    0.25
    Act Density 0.032%

    No Known Activations