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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bunk
    -0.08
     widths
    -0.07
     centered
    -0.07
    内心
    -0.07
     hôm
    -0.07
     whipping
    -0.07
    初
    -0.07
    /me
    -0.07
     thư
    -0.07
    _binding
    -0.07
    POSITIVE LOGITS
     канал
    0.07
    غان
    0.07
    🦚
    0.07
    ߧ
    0.06
    /accounts
    0.06
    AGES
    0.06
     לגמרי
    0.06
    半小时
    0.06
     chặt
    0.06
    _LA
    0.06
    Act Density 0.063%

    No Known Activations