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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    çĶŁ
    -0.68
     defended
    -0.64
    swer
    -0.63
    jit
    -0.62
    ItemImage
    -0.62
    osures
    -0.61
    view
    -0.61
    yl
    -0.60
    urations
    -0.59
    ä¼
    -0.59
    POSITIVE LOGITS
     arrang
    0.69
    abal
    0.67
    voc
    0.66
     graft
    0.66
    ober
    0.66
     Garr
    0.65
     spac
    0.65
    chev
    0.64
     Coch
    0.63
    cules
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.