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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    с
    0.47
     spoonful
    0.38
     meditative
    0.38
    ि
    0.37
    得以
    0.37
     socializing
    0.36
    来看看
    0.36
     harmonious
    0.36
     shepherds
    0.35
    দ্ধ
    0.35
    POSITIVE LOGITS
     been
    0.69
     ollut
    0.55
     sido
    0.55
    ﺭ
    0.53
     BEEN
    0.50
    been
    0.49
    Been
    0.49
     været
    0.48
     bisogno
    0.47
     tenido
    0.47
    Act Density 0.034%

    No Known Activations