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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     happening
    0.80
     elsewhere
    0.80
     certain
    0.71
     criteria
    0.71
     toga
    0.70
     then
    0.69
     among
    0.69
     out
    0.69
     related
    0.69
     criter
    0.69
    POSITIVE LOGITS
    This
    1.20
     Tämä
    1.08
     This
    1.06
    这是一个
    0.98
     Dette
    0.97
    Descripción
    0.96
     Provides
    0.91
    Description
    0.90
    descripcion
    0.89
    这是一
    0.89
    Act Density 0.000%

    No Known Activations