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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    league
    -0.70
     dazz
    -0.65
    м
    -0.64
    spect
    -0.61
     plotted
    -0.60
    Scene
    -0.60
     Mane
    -0.59
    motion
    -0.59
    pie
    -0.57
     Nikola
    -0.57
    POSITIVE LOGITS
    estic
    0.72
     discretion
    0.71
    romy
    0.71
    rocal
    0.68
    ividual
    0.67
    acia
    0.65
    entimes
    0.64
    qua
    0.62
    rium
    0.61
    icate
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.