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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     вов
    -0.14
    oir
    -0.14
     ÑģпÑĢÑı
    -0.13
    atoria
    -0.13
    TEMPL
    -0.13
    ãģĨãģ¡
    -0.13
     ëĭ¤ìļ´ë°Ľê¸°
    -0.12
    levator
    -0.12
    _EXCEPTION
    -0.12
    TestCategory
    -0.12
    POSITIVE LOGITS
     Wid
    0.17
     Pearce
    0.15
    atrix
    0.15
    uchs
    0.14
    ationToken
    0.13
    ycz
    0.13
     Gateway
    0.13
    yk
    0.12
     Ups
    0.12
    ÑģÑĭ
    0.12
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.