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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ١
    1.13
    ۳
    1.08
    ٢
    1.05
    ۲
    1.05
    ٧
    1.02
    ٣
    1.02
    ۱
    0.96
    кс
    0.96
    ۷
    0.94
    ╾
    0.91
    POSITIVE LOGITS
    하거나
    0.99
     rapidamente
    0.91
    on
    0.91
     Rural
    0.90
    ใหม่
    0.89
    comers
    0.88
    都不是
    0.88
    ando
    0.88
    izzard
    0.87
    orrag
    0.87
    Act Density 0.000%

    No Known Activations