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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ư
    -0.18
    ubs
    -0.18
    Ìī
    -0.16
    dÄĽl
    -0.16
    leme
    -0.15
    ermint
    -0.15
    .ru
    -0.15
    [".
    -0.15
    ETO
    -0.15
    Ìģc
    -0.15
    POSITIVE LOGITS
    uez
    0.18
     sites
    0.15
     design
    0.15
    owi
    0.15
     Klein
    0.15
    0.15
     Via
    0.15
     session
    0.15
     rejection
    0.14
    oka
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.