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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    i
    -0.38
      
    -0.37
     
    -0.33
     works
    -0.31
    ,
    -0.30
    .
    -0.30
     most
    -0.30
     Jo
    -0.29
     "
    -0.28
     to
    -0.27
    POSITIVE LOGITS
     queſta
    0.93
    ſelf
    0.88
     ſta
    0.84
     $_(
    0.82
     パンチラ
    0.80
     zwiſchen
    0.79
    ðsíða
    0.79
     geſ
    0.79
     ſeine
    0.77
     dieſes
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.