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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ي
    1.18
    y
    1.10
    erweise
    1.04
    $)$.
    1.04
     muut
    1.02
     nagu
    1.00
    .
    0.99
    ありました
    0.99
    fords
    0.99
     kiek
    0.98
    POSITIVE LOGITS
    女性
    1.29
     unmarried
    1.20
    니아
    1.20
    男性
    1.16
    غ
    1.16
    老
    1.09
     obese
    1.08
     Adolescent
    1.08
     woman
    1.03
    小孩
    1.03
    Act Density 0.148%

    No Known Activations