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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    to
    0.59
    у
    0.57
    го
    0.50
    е
    0.49
    ー
    0.49
    ン
    0.49
    도
    0.48
    ի
    0.45
     to
    0.45
    ص
    0.43
    POSITIVE LOGITS
    0.52
    .
    0.47
     $
    0.47
     suya
    0.45
    N
    0.44
     gyerek
    0.44
     father
    0.43
    orems
    0.43
            
    0.43
     หลังจาก
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.