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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ip
    0.99
    te
    0.80
    pause
    0.80
    ters
    0.79
    leps
    0.78
    ع
    0.77
    tej
    0.76
     duda
    0.75
    ter
    0.74
    ser
    0.74
    POSITIVE LOGITS
     WOMEN
    0.78
    NYC
    0.76
     Σε
    0.75
     Recreational
    0.75
     这
    0.73
     AMA
    0.73
     awakened
    0.71
     оружия
    0.71
     Ту
    0.71
     Doctoral
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.