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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wheelchairs
    0.97
    دع
    0.93
    د
    0.93
    पीजी
    0.93
     Гинд
    0.93
     Pencil
    0.92
     Thời
    0.92
     Character
    0.91
     unexpectedly
    0.91
    могою
    0.91
    POSITIVE LOGITS
    -
    1.09
    '
    1.05
    ’
    1.02
    er
    0.94
    ung
    0.86
    if
    0.86
    verte
    0.86
    iz
    0.84
    *
    0.84
     plupart
    0.84
    Act Density 0.000%

    No Known Activations