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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ...
    -0.19
     ...↵↵
    -0.16
    (...
    -0.16
     (...
    -0.15
    ,...
    -0.15
     вÑģÑij
    -0.15
     ...,
    -0.15
     "...
    -0.14
    ...'
    -0.14
    )...
    -0.14
    POSITIVE LOGITS
     rom
    0.17
    brit
    0.16
    rome
    0.16
    ces
    0.16
    æ¢
    0.15
    ells
    0.15
     Romero
    0.15
    رÙĪÙħ
    0.14
     Rom
    0.14
    rom
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.