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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Travel
    -0.07
    svm
    -0.07
    זי
    -0.07
    素食
    -0.07
    فال
    -0.06
    caf
    -0.06
     unsafe
    -0.06
    透
    -0.06
    模糊
    -0.06
    放缓
    -0.06
    POSITIVE LOGITS
     автор
    0.08
     whopping
    0.07
     курс
    0.07
     принцип
    0.07
     italiane
    0.07
     disciples
    0.07
    Idx
    0.07
    讲究
    0.07
    .clean
    0.07
    kick
    0.07
    Act Density 0.011%

    No Known Activations