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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     polícia
    1.13
     huge
    1.12
     Rá
    1.07
     constipation
    1.06
     Mesmo
    1.03
     redundant
    1.03
    ا
    1.02
    没有任何
    0.99
     трубы
    0.97
     enormously
    0.95
    POSITIVE LOGITS
    +}^{
    1.19
    outil
    1.17
     assicur
    1.14
    bae
    1.13
    ပေါ်
    1.13
     aftermath
    1.12
     consapevole
    1.12
    ned
    1.10
    oby
    1.10
    troops
    1.09
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.