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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Winter
    -0.07
    +m
    -0.07
     lease
    -0.07
     ironic
    -0.06
     suspicious
    -0.06
    ք
    -0.06
     Tri
    -0.06
    土豪
    -0.06
    证
    -0.06
     사진
    -0.06
    POSITIVE LOGITS
     всегда
    0.09
    )["
    0.07
    ([])↵
    0.07
    /logger
    0.07
    ("#{
    0.07
     sanctioned
    0.07
     Neural
    0.07
    "]').
    0.07
    مالك
    0.07
    핸
    0.07
    Act Density 0.392%

    No Known Activations