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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ير
    0.85
    at
    0.79
     lors
    0.77
    TIC
    0.77
     Jeżeli
    0.76
    েশ
    0.73
    is
    0.72
    PCs
    0.70
    o
    0.70
    此类
    0.69
    POSITIVE LOGITS
     опу
    0.68
     компенса
    0.66
     Snowden
    0.64
     helplessness
    0.61
     humble
    0.60
     Alloc
    0.60
     kennel
    0.60
     insign
    0.60
     আসলে
    0.60
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.