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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    agu
    -0.16
    chez
    -0.14
    .rs
    -0.14
    ungs
    -0.14
    ch
    -0.14
    _AS
    -0.14
    cl
    -0.14
    ph
    -0.13
    von
    -0.13
    zell
    -0.13
    POSITIVE LOGITS
     تا
    0.30
    èĩ³
    0.28
    åĪ°
    0.28
     until
    0.27
     till
    0.25
    -J
    0.25
    until
    0.24
     through
    0.23
     -
    0.23
     to
    0.23
    Act Density 0.083%

    No Known Activations