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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     star
    0.96
     nylon
    0.95
     stars
    0.88
    star
    0.79
     Nylon
    0.77
    tum
    0.76
     Star
    0.75
    Star
    0.74
     星
    0.73
    stars
    0.73
    POSITIVE LOGITS
    jø
    0.88
     ഓഫീ
    0.86
    DAD
    0.85
    M
    0.84
    Doctor
    0.82
    În
    0.82
    Để
    0.81
    gh
    0.80
     phiếu
    0.79
     implying
    0.79
    Act Density 0.000%

    No Known Activations