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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Vector
    0.81
     Undoubtedly
    0.80
     Posterior
    0.77
    ('',
    0.70
    ربة
    0.70
    เซ
    0.69
    多彩
    0.69
     posterior
    0.68
     serupa
    0.68
    Mvc
    0.67
    POSITIVE LOGITS
    '
    0.89
     mussten
    0.78
    ب
    0.77
    Owl
    0.75
    метров
    0.74
    ת
    0.73
    었다
    0.72
     prank
    0.71
    `
    0.71
     Punt
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.