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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tiger
    -0.08
     nouvelle
    -0.08
    ombre
    -0.07
     Bucks
    -0.07
     HAPP
    -0.07
     Doe
    -0.07
    ller
    -0.06
    orman
    -0.06
     Daily
    -0.06
    mando
    -0.06
    POSITIVE LOGITS
     inhal
    0.08
    玻璃
    0.07
     Iter
    0.07
    שיעור
    0.07
    _TESTS
    0.07
     substances
    0.07
    bases
    0.07
    )').
    0.07
     (...)
    0.07
     demasi
    0.07
    Act Density 0.010%

    No Known Activations