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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gee
    -0.07
    кие
    -0.07
    ственные
    -0.07
    @Component
    -0.07
     Leigh
    -0.07
     ethics
    -0.07
    xbc
    -0.07
    _DR
    -0.07
     aure
    -0.06
     plate
    -0.06
    POSITIVE LOGITS
    iversary
    0.07
     succès
    0.07
    꾈
    0.07
    soup
    0.07
     defended
    0.07
    _memory
    0.06
    וגש
    0.06
    untime
    0.06
    \Command
    0.06
     sides
    0.06
    Act Density 0.001%

    No Known Activations