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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     attachments
    -0.08
     Extension
    -0.07
     Equip
    -0.07
    ManagerInterface
    -0.07
     plank
    -0.07
    Table
    -0.06
    _Grid
    -0.06
     squads
    -0.06
     checker
    -0.06
     mitigation
    -0.06
    POSITIVE LOGITS
    手动
    0.07
    用工
    0.06
    筹集
    0.06
    seo
    0.06
    变动
    0.06
    ⟡
    0.06
    alış
    0.06
    留学生
    0.06
    /hr
    0.06
    |↵
    0.06
    Act Density 0.026%

    No Known Activations