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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    edar
    -0.07
    ereotype
    -0.07
    要加强
    -0.06
     participates
    -0.06
     yapıyor
    -0.06
    햋
    -0.06
     StartTime
    -0.06
    ateg
    -0.06
    yb
    -0.06
    plusplus
    -0.06
    POSITIVE LOGITS
     basis
    0.08
    (with
    0.07
    老妈
    0.07
    larına
    0.07
     safely
    0.07
    (Page
    0.07
    Tests
    0.07
     cosine
    0.07
     component
    0.07
     scale
    0.07
    Act Density 0.004%

    No Known Activations