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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Compass
    -0.83
    ulhu
    -0.80
     Doodle
    -0.70
     Dickinson
    -0.69
     appraisal
    -0.69
     EntityItem
    -0.67
     cx
    -0.65
    uers
    -0.65
     Guru
    -0.64
     ingred
    -0.63
    POSITIVE LOGITS
    based
    1.18
    sized
    1.17
    themed
    1.09
    induced
    1.00
    bodied
    1.00
    series
    0.96
    centered
    0.95
    powered
    0.95
    scale
    0.94
    style
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.