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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Internet
    0.86
     people
    0.85
     adlı
    0.79
    Modifier
    0.78
     Collabor
    0.77
     Subscribers
    0.75
     paysans
    0.75
     Nationalist
    0.74
     Overnight
    0.74
    <
    0.74
    POSITIVE LOGITS
     а
    1.16
     cabinetry
    0.98
     встроен
    0.98
    ке
    0.98
     gyro
    0.96
     andRow
    0.95
     atrium
    0.94
    к
    0.93
     знаю
    0.93
     expertly
    0.93
    Act Density 0.049%

    No Known Activations