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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    0.57
    int
    0.50
    order
    0.50
    :
    0.48
     l
    0.48
    ind
    0.48
    ,
    0.48
    l
    0.47
    ong
    0.46
    com
    0.46
    POSITIVE LOGITS
     теркәлү
    0.56
     кеңсеси
    0.49
     فونٹ
    0.47
     бушлай
    0.46
     уйнагыз
    0.46
     кеңселер
    0.45
     اولمپس
    0.45
     фаразы
    0.45
     депозиттик
    0.45
    悝
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.