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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _CLI
    -0.08
    ус
    -0.07
    촥
    -0.07
    _COPY
    -0.07
    יך
    -0.07
    릎
    -0.07
    ❱
    -0.07
    のに
    -0.07
    떄
    -0.06
     Mitt
    -0.06
    POSITIVE LOGITS
    unidad
    0.07
    -owned
    0.07
    uestion
    0.06
    ｍ
    0.06
     prefixed
    0.06
    前来
    0.06
     defenders
    0.06
     worship
    0.06
     experiences
    0.06
     Ihrem
    0.06
    Act Density 0.026%

    No Known Activations