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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unemploy
    -0.80
    ilitary
    -0.76
     hire
    -0.75
    holding
    -0.73
    enegger
    -0.73
     reinstated
    -0.71
     hired
    -0.69
     unemployed
    -0.68
    ally
    -0.65
    uner
    -0.64
    POSITIVE LOGITS
    ICLE
    0.86
     Brush
    0.78
    BUG
    0.77
    ipeg
    0.77
    minster
    0.71
    ĺħ
    0.67
     Thumbnails
    0.67
    IJ
    0.66
    ËĪ
    0.65
    £ı
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.