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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    b
    0.44
    c
    0.39
    1
    0.39
    t
    0.39
    2
    0.39
    0
    0.38
    ing
    0.38
    3
    0.36
    -
    0.35
    0.35
    POSITIVE LOGITS
     dieci
    0.45
     interrom
    0.41
     oito
    0.39
     entusiasmo
    0.38
     vijf
    0.38
     linguagem
    0.38
     zweimal
    0.38
     uomini
    0.37
     zusamm
    0.37
     dotato
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.