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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exorbit
    0.95
     ChangeNotifier
    0.87
    𝕖
    0.86
     sewn
    0.85
     whose
    0.85
     symbolically
    0.82
     inextricably
    0.82
    ably
    0.81
     meaningfully
    0.81
     knowledgeable
    0.79
    POSITIVE LOGITS
    ysing
    1.06
    ঙ্গিক
    0.99
    තුර
    0.97
    €™
    0.97
     sclerosis
    0.96
    𝙫
    0.94
     друзья
    0.94
     cara
    0.93
     poor
    0.92
     Bagaimana
    0.92
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.