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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     interchangeably
    0.63
    мент
    0.63
    фы
    0.62
    }={\
    0.61
     هم
    0.61
    ℉
    0.60
    era
    0.59
     phrase
    0.59
     middlewares
    0.59
    льных
    0.59
    POSITIVE LOGITS
     saját
    0.80
    蘄
    0.77
    纪念
    0.77
     자신의
    0.77
     допомогти
    0.76
    ící
    0.75
    幫助
    0.75
     ilişk
    0.75
    资源的
    0.73
    ৬
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.