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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nts
    -0.28
    æĸ°å¸¸æĢģ
    -0.27
    _fx
    -0.26
    ROY
    -0.26
    URY
    -0.25
    åı¨
    -0.25
    ä¼İ
    -0.25
    ipay
    -0.24
    èı²
    -0.24
    ä¹Łå¥½
    -0.24
    POSITIVE LOGITS
     drafts
    0.29
     sac
    0.27
     SAC
    0.26
    ä¼łè¯´
    0.26
    eto
    0.26
    -drop
    0.26
     Knot
    0.25
    elson
    0.25
    ald
    0.25
     blind
    0.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.