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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    M
    0.63
    Kemudian
    0.59
     Затем
    0.57
     یا
    0.56
    И
    0.56
    L
    0.56
    Then
    0.56
    Z
    0.53
     või
    0.53
    antaranya
    0.52
    POSITIVE LOGITS
     there
    1.28
     it
    1.05
     they
    0.95
     most
    0.89
     despite
    0.88
     theres
    0.88
     nobody
    0.87
     disagreements
    0.87
     discrepancies
    0.83
     proponents
    0.83
    Act Density 1.366%

    No Known Activations