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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    廳
    -0.07
    /Add
    -0.07
    .fade
    -0.07
     הזה
    -0.07
    锦
    -0.07
    Haz
    -0.07
     bones
    -0.07
    .fe
    -0.07
    -sl
    -0.07
    So
    -0.07
    POSITIVE LOGITS
    operate
    0.07
    ("""↵
    0.06
    rary
    0.06
    预备
    0.06
    oug
    0.06
    וקר
    0.06
     einen
    0.06
     önlem
    0.06
     brown
    0.06
    뎠
    0.06
    Act Density 0.000%

    No Known Activations