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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dried
    0.96
     charming
    0.94
     Contrary
    0.88
     Thick
    0.85
     Calm
    0.83
     Drought
    0.82
     Graham
    0.80
     thick
    0.80
     charm
    0.80
     Broken
    0.79
    POSITIVE LOGITS
    ب
    1.03
    ⎟
    0.96
    labor
    0.94
    mente
    0.94
    ther
    0.90
    ‬‬
    0.89
    कैसे
    0.89
    ကြည့်
    0.88
     laug
    0.86
    pre
    0.84
    Act Density 0.000%

    No Known Activations