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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãģĸ
    -0.07
    DEX
    -0.07
    ãĥĥãĤ°
    -0.07
    ä¼ģ
    -0.07
    INARY
    -0.07
    _mex
    -0.06
    aal
    -0.06
    deo
    -0.06
    ihu
    -0.06
    .usage
    -0.06
    POSITIVE LOGITS
     girls
    0.08
     Sphere
    0.07
     Girls
    0.07
     unmarried
    0.07
     villagers
    0.06
     Distrib
    0.06
     Municip
    0.06
     dew
    0.06
     té
    0.06
    herits
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.