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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    apers
    -0.77
    aper
    -0.72
    grain
    -0.72
    ++++++++
    -0.70
    .............
    -0.69
    Agg
    -0.67
    âĸ¬
    -0.67
    bodied
    -0.66
    cock
    -0.64
     sal
    -0.64
    POSITIVE LOGITS
    rity
    0.85
    agate
    0.74
    staking
    0.72
    byn
    0.65
    terday
    0.63
    ameron
    0.63
     Cable
    0.62
     Weiner
    0.62
    olkien
    0.62
     Regions
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.