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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sole
    -0.08
     Birliği
    -0.08
    秭
    -0.07
     Chancellor
    -0.07
     software
    -0.07
    Generation
    -0.07
    涂料
    -0.07
    -Series
    -0.07
     IX
    -0.07
    -negative
    -0.07
    POSITIVE LOGITS
    🕢
    0.07
    已经在
    0.06
    Р
    0.06
    .User
    0.06
    ﻣ
    0.06
    айл
    0.06
    _example
    0.06
     verificar
    0.06
    /text
    0.06
    味道
    0.06
    Act Density 0.002%

    No Known Activations