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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Growth
    0.52
    man
    0.50
    nor
    0.50
    W
    0.49
    \
    0.49
    ich
    0.48
     Veterinary
    0.47
    û
    0.47
    UT
    0.46
    OT
    0.45
    POSITIVE LOGITS
     alcoved
    0.66
     caloric
    0.62
     intruders
    0.59
     garante
    0.57
     cardiaque
    0.57
     jednego
    0.56
     جاه
    0.55
     osobe
    0.55
     segundos
    0.55
     momen
    0.54
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.