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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     לשמור
    -0.07
    --)
    -0.07
     Murdoch
    -0.07
    =''):↵
    -0.07
     comme
    -0.07
    -0.07
    传奇里面
    -0.07
    °C
    -0.07
    -0.07
     Bowie
    -0.07
    POSITIVE LOGITS
     класс
    0.08
     popularity
    0.08
    LOTS
    0.07
     Initialization
    0.07
    隆
    0.07
    نع
    0.07
     Loving
    0.07
    oped
    0.07
    𝑓
    0.07
    _release
    0.06
    Act Density 0.059%

    No Known Activations