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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ws
    1.06
    sa
    1.04
    '
    1.01
    atering
    0.99
    gn
    0.97
    rh
    0.96
    '/
    0.90
    sg
    0.86
    gs
    0.85
    ýv
    0.85
    POSITIVE LOGITS
     Paper
    0.99
     paper
    0.95
     Papers
    0.89
     Seneca
    0.88
     papers
    0.88
     Treatise
    0.86
     Kondo
    0.85
     Papier
    0.84
    Paper
    0.83
     Concise
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.