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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    5
    0.91
    원
    0.90
    0
    0.90
    9
    0.89
    4
    0.88
    2
    0.86
    3
    0.84
     zkušen
    0.82
    পূর্ব
    0.79
    1
    0.79
    POSITIVE LOGITS
    hob
    0.81
     Peb
    0.76
     Wasn
    0.71
    𝕙
    0.71
    lingen
    0.71
    𝗛
    0.71
    lerinin
    0.70
     Frieden
    0.70
    していました
    0.69
     Pebble
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.