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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exorbit
    1.37
     despertar
    1.24
    腴
    1.23
     Tolst
    1.22
     atthakath
    1.21
     balo
    1.21
     Ugar
    1.20
    iemi
    1.19
     visibly
    1.18
     выпуска
    1.17
    POSITIVE LOGITS
    к
    1.09
    א
    1.00
    ク
    0.94
     comb
    0.93
    Four
    0.91
    r
    0.91
    "
    0.91
    шенный
    0.89
    िक
    0.89
    검
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.