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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and their attributes related to user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.96
    <unused68>
    -0.89
    <unused52>
    -0.89
    <unused28>
    -0.88
    [@BOS@]
    -0.88
    <pad>
    -0.88
    <unused51>
    -0.88
    <unused74>
    -0.88
    <unused16>
    -0.88
    <unused8>
    -0.88
    POSITIVE LOGITS
    seguida
    0.28
    @[+][
    0.26
     føl
    0.23
     helemaal
    0.23
     göz
    0.23
    .
    0.22
     ح
    0.22
     vivement
    0.21
    ærk
    0.21
     Schnell
    0.21
    Act Density 0.184%

    No Known Activations