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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ien
    1.21
    ou
    1.08
    uest
    1.04
    amp
    1.02
    arr
    1.01
    az
    1.00
    ong
    0.95
    nan
    0.94
    bert
    0.93
    sen
    0.93
    POSITIVE LOGITS
     centric
    1.52
    𝘳
    1.42
     clings
    1.41
     Pagination
    1.39
     pagination
    1.38
     />}
    1.33
     sheer
    1.32
    1.31
    Serialize
    1.31
     څنګه
    1.31
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.