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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    accompan
    -0.78
     Orig
    -0.69
    inery
    -0.68
    cious
    -0.68
    izabeth
    -0.66
    rite
    -0.65
     exceptions
    -0.65
     forks
    -0.64
     wed
    -0.64
    adle
    -0.61
    POSITIVE LOGITS
    ulas
    0.86
    ãĥ´ãĤ¡
    0.70
    ãĤ®
    0.70
    PsyNetMessage
    0.67
     Schwarzenegger
    0.65
    ãĤ±
    0.64
    ico
    0.63
     Tycoon
    0.63
    ula
    0.62
    bal
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.