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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iction
    1.04
    achine
    0.99
    或
    0.98
    hetical
    0.97
    рованная
    0.93
    ura
    0.92
     nas
    0.92
    reatment
    0.90
    ared
    0.89
    ة
    0.89
    POSITIVE LOGITS
     Technik
    1.19
     faisons
    1.18
     siamo
    1.17
     espaces
    1.14
    Waar
    1.14
    hutang
    1.14
     critères
    1.13
     Kemudian
    1.12
     Sein
    1.11
     Allí
    1.08
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.