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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     RÉ
    0.93
     Même
    0.86
     ETA
    0.84
    ⌯
    0.79
     Outputs
    0.78
     Що
    0.77
     Gé
    0.77
     tarses
    0.77
    俥
    0.77
     Drž
    0.77
    POSITIVE LOGITS
    st
    1.13
    m
    1.02
    man
    1.00
    g
    0.99
    c
    0.95
    se
    0.93
    maker
    0.90
    son
    0.89
    mm
    0.89
    ms
    0.89
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.