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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    1.12
     vicinity
    1.09
    ution
    1.05
    一级
    1.03
    ignored
    1.03
    ა
    1.03
     shortcut
    1.01
     fallback
    0.98
     beverage
    0.97
    اتر
    0.96
    POSITIVE LOGITS
     Puede
    1.21
     Gebrauch
    1.16
    Puede
    1.10
    氰
    1.10
     gebruik
    1.09
    ">−</
    1.08
     einfachen
    1.07
     lijkt
    1.06
    <bos>
    1.06
     freuen
    1.05
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.