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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    asso
    -0.07
    Mage
    -0.07
    <J
    -0.07
    (Test
    -0.07
    scanf
    -0.07
    멎
    -0.07
    óst
    -0.07
    grass
    -0.07
    jack
    -0.07
     Test
    -0.06
    POSITIVE LOGITS
     wir
    0.08
    uiten
    0.07
    ir
    0.07
    嗲
    0.07
     expiration
    0.07
     פר
    0.07
    gh
    0.07
    姆
    0.07
    完全可以
    0.06
     omdat
    0.06
    Act Density 0.049%

    No Known Activations