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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    apper
    -0.77
    psons
    -0.75
    obs
    -0.70
    inder
    -0.69
    ymes
    -0.67
    urg
    -0.66
    iets
    -0.66
    acho
    -0.65
    IME
    -0.65
    ugs
    -0.65
    POSITIVE LOGITS
    Introduced
    0.70
    Dragon
    0.67
    Soviet
    0.66
     mileage
    0.65
    Driver
    0.64
    Conclusion
    0.64
    secution
    0.64
     Continued
    0.63
    CONCLUS
    0.62
     Emir
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.