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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ursprünglich
    0.54
     zufrieden
    0.52
     bitterly
    0.52
    بیه
    0.50
     erlä
    0.49
    ngths
    0.48
     sämt
    0.48
     wyp
    0.48
     recast
    0.48
     natürlich
    0.48
    POSITIVE LOGITS
    plings
    0.51
     స
    0.49
    Buyer
    0.49
     ह
    0.48
     Lind
    0.48
     किम
    0.47
    al
    0.46
    rons
    0.46
    rene
    0.45
     निजा
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.