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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reputation
    0.57
     reportedly
    0.57
     skepticism
    0.56
     prospects
    0.52
    леты
    0.51
     predicament
    0.51
     reputations
    0.50
     patriotic
    0.50
    男
    0.50
     lira
    0.49
    POSITIVE LOGITS
     будто
    0.86
    ică
    0.71
     sesuatu
    0.68
     Something
    0.67
    Something
    0.66
     resalt
    0.64
     ceva
    0.64
    ildren
    0.63
     gitu
    0.63
     etwas
    0.62
    Act Density 0.283%

    No Known Activations