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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     patterning
    0.41
    alia
    0.39
    uset
    0.38
    统计
    0.36
    ALIGN
    0.36
    ixes
    0.36
     createUser
    0.36
     User
    0.36
    ework
    0.35
    尟
    0.35
    POSITIVE LOGITS
     Sonnen
    0.50
     sejumlah
    0.42
     nessuna
    0.42
     Sumo
    0.40
     naturais
    0.39
     Hendrik
    0.39
     aucune
    0.39
     Moroccan
    0.39
     هیچ
    0.38
     داخلی
    0.38
    Act Density 0.004%

    No Known Activations