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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     and
    0.93
     was
    0.93
    ul
    0.84
    :
    0.77
    ait
    0.70
    \
    0.70
    ches
    0.69
    ía
    0.68
    uo
    0.68
    ong
    0.66
    POSITIVE LOGITS
    8
    1.10
    Z
    1.02
    G
    0.98
    7
    0.96
    9
    0.96
    6
    0.93
    W
    0.89
    ме
    0.89
    2
    0.88
    H
    0.87
    Act Density 0.000%

    No Known Activations