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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ter
    1.98
    ів
    1.92
    ου
    1.90
    ى
    1.55
    th
    1.52
    ل
    1.51
    го
    1.47
    Ы
    1.46
    ל
    1.45
    ية
    1.45
    POSITIVE LOGITS
     olympiques
    1.40
     subtilis
    1.38
     Cavs
    1.37
     dê
    1.32
     sums
    1.31
     croissants
    1.31
     leptons
    1.30
     suspects
    1.30
     partout
    1.29
     cheesecake
    1.28
    Act Density 0.000%

    No Known Activations