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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bart
    -0.08
     defender
    -0.07
    靬
    -0.07
     Cobb
    -0.07
    靼
    -0.07
    接受了
    -0.07
     Bắc
    -0.07
    력을
    -0.07
    當您
    -0.07
     recruits
    -0.07
    POSITIVE LOGITS
    _Input
    0.07
    Toolkit
    0.07
     installations
    0.07
    (Sql
    0.06
    ('+
    0.06
    RE
    0.06
    /widgets
    0.06
     missiles
    0.06
    [];
↵
    0.06
    annotate
    0.06
    Act Density 0.001%

    No Known Activations