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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sigma
    -0.07
    k
    -0.07
    .stack
    -0.07
     vp
    -0.07
     strike
    -0.07
    (slug
    -0.07
    	stack
    -0.07
    ysters
    -0.07
    ick
    -0.06
    ards
    -0.06
    POSITIVE LOGITS
    냈
    0.08
    FlowLayout
    0.07
     inequalities
    0.07
    出入
    0.07
    �
    0.07
    落ち着
    0.07
    丰硕
    0.07
    ,{"
    0.07
    亮丽
    0.07
     בנוסף
    0.07
    Act Density 0.002%

    No Known Activations