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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     characterize
    0.83
    πο
    0.80
    函數
    0.77
     be
    0.75
    ↵
    0.75
     emphasize
    0.75
    看護
    0.73
    𝐪
    0.71
    氯
    0.71
    angular
    0.71
    POSITIVE LOGITS
    "})
    0.91
     сейчас
    0.88
     recorr
    0.86
     bliss
    0.86
     propias
    0.85
    "])
    0.83
     vistas
    0.83
     felicidad
    0.80
     vidas
    0.78
     दिशा
    0.77
    Act Density 0.000%

    No Known Activations