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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     the
    0.67
     a
    0.66
     an
    0.50
     а
    0.50
     your
    0.48
     it
    0.47
    قول
    0.47
    an
    0.43
    ut
    0.43
    eb
    0.43
    POSITIVE LOGITS
     havde
    0.63
    ️⃣
    0.56
    ين
    0.54
    ⃣
    0.53
     horas
    0.52
     ήταν
    0.51
     был
    0.49
     horaires
    0.49
     cardiaque
    0.49
    했던
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.