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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    D
    0.99
     אז
    0.84
    locked
    0.84
    Strip
    0.83
    the
    0.81
    Grid
    0.81
    一个
    0.80
    Ch
    0.80
    Width
    0.80
    Cube
    0.79
    POSITIVE LOGITS
    iyot
    1.00
     gestire
    0.98
     sintomi
    0.96
     mujer
    0.94
     dhammo
    0.94
    ⁱ
    0.94
     GAO
    0.94
     poursuivre
    0.94
    ለሁ
    0.92
    ție
    0.92
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.