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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ó
    1.20
    {
    1.16
     at
    1.13
    ü
    1.13
    ى
    1.10
    ।
    1.08
    }.
    1.04
    IM
    1.03
    ).
    1.01
    ['
    1.01
    POSITIVE LOGITS
    ди
    1.19
    ные
    1.18
    ών
    1.13
    ли
    1.09
    ная
    1.09
    ри
    1.05
    quement
    1.04
    ク
    1.03
    с
    1.01
    engkapi
    1.00
    Act Density 0.000%

    No Known Activations