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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     frank
    -0.07
    fname
    -0.07
    拽
    -0.07
     fours
    -0.06
    A
    -0.06
    ("@
    -0.06
    滗
    -0.06
     egt
    -0.06
     (@
    -0.06
    instagram
    -0.06
    POSITIVE LOGITS
     дети
    0.08
    dating
    0.07
    _CTL
    0.07
     enemy
    0.07
     tasted
    0.07
    ']>;↵
    0.07
    初めて
    0.07
    .EditorButton
    0.07
    stay
    0.07
    古い
    0.06
    Act Density 0.001%

    No Known Activations