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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     borrowing
    0.66
     Borrow
    0.56
     borrow
    0.55
    借
    0.53
    Borrow
    0.51
    borrow
    0.50
     borrows
    0.48
     borrowings
    0.45
     borrowed
    0.45
    köz
    0.41
    POSITIVE LOGITS
    𝙰
    0.38
    リューション
    0.37
    Credit
    0.37
     aktu
    0.37
     Heg
    0.37
     Ded
    0.36
     Hei
    0.36
    classAttribute
    0.36
    As
    0.35
    Additionally
    0.35
    Act Density 0.000%

    No Known Activations