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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ๘
    0.95
    ๙
    0.93
    xl
    0.92
    ust
    0.92
    nb
    0.90
    ➁
    0.90
     esto
    0.87
     vállalat
    0.86
    gil
    0.86
    ๓
    0.86
    POSITIVE LOGITS
     RMSE
    0.95
     underestimate
    0.94
     Optics
    0.91
    ती
    0.91
     romantic
    0.90
     quantify
    0.90
     pathophysiology
    0.86
    ре
    0.86
     airborne
    0.86
    ateful
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.