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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    1.25
    in
    1.23
    m
    1.23
    ра
    1.20
    ol
    1.13
    to
    1.13
    ta
    1.13
    at
    1.13
    can
    1.12
    the
    1.11
    POSITIVE LOGITS
     and
    1.28
     one
    1.11
     ۲
    0.97
    نی
    0.96
    یل
    0.95
     by
    0.90
    ן
    0.90
    انی
    0.89
     aisle
    0.89
     hept
    0.88
    Act Density 0.000%

    No Known Activations