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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ufact
    -0.87
     mistaken
    -0.74
    furt
    -0.73
    wagen
    -0.72
     misunderstanding
    -0.71
     Droid
    -0.69
     miscon
    -0.69
    forced
    -0.68
    manufact
    -0.67
    placed
    -0.66
    POSITIVE LOGITS
    QUI
    0.82
    ģĸ
    0.68
    avorite
    0.67
    Param
    0.66
     census
    0.65
    »Ĵ
    0.64
     astroph
    0.64
    »
    0.64
     Meditation
    0.63
    Stats
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.