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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     shaping
    -0.07
     dotyczące
    -0.07
     Ging
    -0.07
    hi
    -0.07
    🆕
    -0.07
     international
    -0.07
    德州
    -0.07
    %X
    -0.07
    咫
    -0.07
     detection
    -0.07
    POSITIVE LOGITS
    _contains
    0.08
    ;
↵
    0.07
     Jenna
    0.06
    menus
    0.06
     Marian
    0.06
     spouses
    0.06
    --
↵
    0.06
    Noise
    0.06
    און
    0.06
    oda
    0.06
    Act Density 0.008%

    No Known Activations