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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oha
    0.48
    red
    0.46
    iance
    0.46
    ról
    0.46
    feb
    0.45
    us
    0.44
    billing
    0.44
     aggrieved
    0.44
    education
    0.43
     сдела
    0.43
    POSITIVE LOGITS
     consistente
    0.53
     inconsist
    0.52
    ﺍ
    0.50
    مت
    0.49
    嗉
    0.49
    לי
    0.48
     伊
    0.48
     ק
    0.48
    ípios
    0.48
     previs
    0.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.