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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    с
    1.18
    an
    1.08
    ab
    1.01
    up
    0.96
    ks
    0.94
    とり
    0.93
     -
    0.92
    ệu
    0.91
    chten
    0.91
     Dzięki
    0.90
    POSITIVE LOGITS
     dominions
    1.58
     axioms
    1.50
     cardia
    1.49
     mercantil
    1.46
     adultery
    1.46
     scenery
    1.46
     whats
    1.45
     inaugural
    1.44
     insolvency
    1.44
    tion
    1.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.