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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     in
    1.08
    서
    1.02
    el
    1.00
    elij
    0.99
    c
    0.98
    ви
    0.98
    ем
    0.97
    在
    0.97
     νέ
    0.96
     μεγά
    0.95
    POSITIVE LOGITS
    '
    1.50
    '।
    1.28
    ',
    1.24
    ۔
    1.15
    é
    1.14
    ’।
    1.12
    OC
    1.11
    unt
    1.09
    ↵
    1.06
    اں
    1.05
    Act Density 0.000%

    No Known Activations