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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     aus
    -0.07
    sein
    -0.06
     nouvel
    -0.06
     acheter
    -0.06
     vàng
    -0.06
    оч
    -0.06
     favor
    -0.06
    超高
    -0.06
     positioning
    -0.06
     khóa
    -0.06
    POSITIVE LOGITS
    .Fatal
    0.07
    😛
    0.07
    bold
    0.07
     mustard
    0.07
    깉
    0.07
    (Dictionary
    0.07
     contrib
    0.07
    этаж
    0.07
    strike
    0.07
    _based
    0.07
    Act Density 0.018%

    No Known Activations