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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     сделать
    1.32
    йс
    1.25
     lazy
    1.25
     irradi
    1.24
     сообщи
    1.20
    ޏ
    1.20
     UNITS
    1.19
     juez
    1.19
     resurrect
    1.19
    hiqdev
    1.18
    POSITIVE LOGITS
    max
    1.10
    the
    1.09
    min
    1.08
    gift
    1.01
    water
    1.00
    Future
    1.00
    divided
    0.99
    dict
    0.98
    where
    0.98
    m
    0.98
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.