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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    TextColor
    -0.84
    MRI
    -0.78
    KEN
    -0.77
    roo
    -0.75
    oof
    -0.75
    git
    -0.74
    assetsadobe
    -0.73
    arna
    -0.72
    thumbnails
    -0.71
    ww
    -0.71
    POSITIVE LOGITS
    ancies
    0.82
     downs
    0.68
    ngth
    0.66
     stakes
    0.66
    owship
    0.66
     rated
    0.65
     Downs
    0.64
     Pax
    0.64
     summons
    0.63
     spit
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.