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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dispositivo
    0.42
     Tracy
    0.40
     Grant
    0.38
    南
    0.38
    ни
    0.37
    Mark
    0.37
     Install
    0.37
     tiek
    0.37
     That
    0.37
     Mary
    0.37
    POSITIVE LOGITS
    efeuille
    0.46
     isle
    0.45
     forecasts
    0.44
    oches
    0.43
    azah
    0.42
     assaulted
    0.41
    ophages
    0.41
    @",
    0.41
    oug
    0.41
     adorned
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.