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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    !
    1.49
    ?!
    1.38
    !”
    1.32
    %!
    1.32
     (
    1.31
    !“
    1.27
    ！（
    1.27
     (@
    1.23
     [
    1.22
    !!
    1.22
    POSITIVE LOGITS
     underpinned
    1.58
     fuelled
    1.56
    ﹒
    1.52
    <unused1408>
    1.45
     शुर
    1.34
     sparked
    1.34
     Обычно
    1.32
    üche
    1.32
    𝓀
    1.30
     เชื่อ
    1.29
    Act Density 0.093%

    No Known Activations