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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anko
    -0.19
    oucher
    -0.16
    akh
    -0.16
    illin
    -0.15
    iron
    -0.15
    TestMethod
    -0.15
    ulumi
    -0.15
    igos
    -0.15
    zi
    -0.14
    meldung
    -0.14
    POSITIVE LOGITS
    bia
    0.17
     plein
    0.14
    owl
    0.14
    áz
    0.14
    ventions
    0.14
    ër
    0.14
     chances
    0.14
     Mayo
    0.14
    eded
    0.13
    /un
    0.13
    Act Density 0.013%

    No Known Activations