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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Corey
    -0.30
     Blind
    -0.30
    letal
    -0.29
    esome
    -0.27
    blind
    -0.26
    kker
    -0.26
    åij½
    -0.26
    (core
    -0.26
    LETTE
    -0.26
    -blind
    -0.25
    POSITIVE LOGITS
    æı´
    0.27
    mast
    0.27
     ÙħÙĨÙĩا
    0.25
    .fit
    0.25
     disse
    0.24
     Äijúng
    0.24
     trace
    0.24
    ame
    0.24
    åľ¯
    0.24
     proc
    0.24
    Act Density 0.148%

    No Known Activations

    This feature has no known activations.