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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    א
    0.74
    એ
    0.72
     not
    0.71
    તે
    0.69
     delicious
    0.68
    ೆಯೇ
    0.68
    お
    0.68
     coffee
    0.66
     appetite
    0.65
    /)
    0.64
    POSITIVE LOGITS
     живут
    0.91
     состоит
    0.89
     condiciones
    0.89
     жить
    0.89
     являются
    0.88
     ഗുരു
    0.88
     recibieron
    0.86
     vivir
    0.84
     candidatos
    0.83
     creencias
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.