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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uers
    -0.73
    etts
    -0.69
    Ô
    -0.69
    ocene
    -0.69
    wagen
    -0.69
    ø
    -0.69
     Bayer
    -0.68
     Columb
    -0.68
     Restaur
    -0.68
    uez
    -0.67
    POSITIVE LOGITS
    inyl
    0.78
    heartedly
    0.74
    graded
    0.74
    produ
    0.71
     Luna
    0.66
    gio
    0.66
    forming
    0.65
     Metatron
    0.65
    cause
    0.65
    shine
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.