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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Eleanor
    -0.71
    ervation
    -0.68
     Congressional
    -0.66
     peril
    -0.66
     Opp
    -0.65
     Measure
    -0.65
     Fleming
    -0.64
     Aging
    -0.62
     ACTION
    -0.59
    unda
    -0.59
    POSITIVE LOGITS
    reads
    0.77
    Rex
    0.75
     Toro
    0.70
    eele
    0.70
     Minion
    0.70
    addons
    0.69
    hedon
    0.69
    ascus
    0.68
    mond
    0.67
    won
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.