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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.30
    om
    1.20
    im
    1.18
    ar
    1.00
    el
    0.91
    at
    0.91
    ab
    0.89
    ia
    0.89
    oe
    0.89
    am
    0.86
    POSITIVE LOGITS
     Хотя
    1.15
    𝚈
    1.09
     Они
    1.05
     Antwort
    1.05
     Langkah
    1.05
     Där
    1.05
     อย่าง
    1.02
     สุด
    1.02
    𝙰
    1.02
     Apesar
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.