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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    il
    0.63
    Sincerely
    0.63
     Live
    0.62
     vehemently
    0.61
     debunk
    0.61
     deserves
    0.60
     Bohr
    0.60
     Valeria
    0.59
     Agn
    0.59
     Patreon
    0.58
    POSITIVE LOGITS
     在
    0.63
     في
    0.62
    বা
    0.62
     cama
    0.61
     bebek
    0.61
    但在
    0.59
     fábrica
    0.59
     fabricación
    0.58
     الكهربائيه
    0.58
     ஆகியவற்ற
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.