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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    asin
    -0.81
    alpha
    -0.81
    been
    -0.77
    attribute
    -0.73
    ayers
    -0.72
    RESULTS
    -0.72
    party
    -0.71
    gone
    -0.70
    finished
    -0.69
    LEASE
    -0.66
    POSITIVE LOGITS
     Tiff
    0.71
    UCT
    0.69
     Noon
    0.63
     Naj
    0.63
     maj
    0.63
     Bul
    0.63
     Stamp
    0.62
     Zeal
    0.61
     Heller
    0.60
     veter
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.