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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    en
    1.29
     desire
    1.17
    es
    1.08
    gray
    0.98
     жела
    0.98
     والخ
    0.94
     Authorization
    0.92
    in
    0.91
    m
    0.91
    faux
    0.91
    POSITIVE LOGITS
     marít
    1.32
     postérieures
    1.25
     públicas
    1.23
     considér
    1.20
    рани
    1.18
     tendrá
    1.16
     aé
    1.15
    irán
    1.15
     Dacă
    1.15
    ленные
    1.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.