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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    linger
    -0.18
    ÏĦί
    -0.15
    ling
    -0.15
    _CLI
    -0.14
    bis
    -0.14
    wards
    -0.14
    iddles
    -0.14
    tees
    -0.14
    agne
    -0.14
     lok
    -0.14
    POSITIVE LOGITS
    ucer
    0.17
    uxtap
    0.15
    aub
    0.14
    озем
    0.14
    iley
    0.14
    омÑĥ
    0.14
    ucha
    0.14
    ucken
    0.14
     mechanics
    0.14
    indent
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.