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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ellä
    0.95
    är
    0.92
     tā
    0.89
     کرل
    0.89
     যেটি
    0.89
    ánd
    0.88
     féd
    0.88
    өк
    0.87
     précie
    0.86
    innon
    0.85
    POSITIVE LOGITS
     to
    1.58
    to
    1.26
     a
    1.23
    </strong>
    1.10
    1.09
    de
    1.07
     at
    1.05
    ש
    0.99
    0.97
    大
    0.96
    Act Density 0.000%

    No Known Activations