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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ertil
    -0.07
    加紧
    -0.07
     ber
    -0.07
    伶
    -0.07
     Hugh
    -0.07
    зем
    -0.07
    _assign
    -0.07
    _arc
    -0.07
    振
    -0.07
    ưỡng
    -0.07
    POSITIVE LOGITS
    ,default
    0.07
    妫
    0.07
     pivot
    0.07
    descending
    0.07
     childish
    0.07
    🐥
    0.07
     setups
    0.07
     Parad
    0.06
    话题
    0.06
    ��이터
    0.06
    Act Density 0.021%

    No Known Activations