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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _bm
    -0.08
    DEPEND
    -0.07
    :The
    -0.07
    .preference
    -0.07
    STATE
    -0.07
    .action
    -0.06
    沐
    -0.06
    你看
    -0.06
     Mara
    -0.06
     ran
    -0.06
    POSITIVE LOGITS
    白菜
    0.08
    $where
    0.08
     NEW
    0.07
    .EditorButton
    0.07
    -feedback
    0.07
    افة
    0.07
    ⧪
    0.07
    仓库
    0.07
    (sentence
    0.07
     airports
    0.07
    Act Density 0.000%

    No Known Activations