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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ED
    0.52
    Κ
    0.50
    Το
    0.48
    Politics
    0.48
    ’
    0.47
    Choose
    0.47
    Ý
    0.47
    Category
    0.46
    Π
    0.46
    ūs
    0.45
    POSITIVE LOGITS
     сложно
    0.50
     хвата
    0.46
     negar
    0.45
     ford
    0.44
    форд
    0.44
     trans
    0.43
     regional
    0.43
    ீர்
    0.43
     такие
    0.43
     quantitative
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.