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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ateliers
    0.83
    та
    0.81
    बता
    0.78
    ک
    0.78
     Maddie
    0.75
    ४
    0.75
    avirus
    0.73
     occupiers
    0.73
     وعلى
    0.72
     Scouts
    0.71
    POSITIVE LOGITS
    на
    1.06
    ра
    1.00
    ри
    1.00
    }$.
    0.97
    ן
    0.95
     등의
    0.94
    ний
    0.91
     recoge
    0.88
    면
    0.88
    ور
    0.84
    Act Density 4.479%

    No Known Activations