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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     traged
    -0.83
    ortium
    -0.82
    aspers
    -0.81
    acebook
    -0.79
    roup
    -0.73
    pta
    -0.72
     Gupta
    -0.70
    icipated
    -0.70
     blat
    -0.69
     seiz
    -0.67
    POSITIVE LOGITS
    ready
    0.77
    è£ħ
    0.69
    istar
    0.69
    ALLY
    0.68
    >>
    0.66
    maker
    0.66
    ¬
    0.64
    liners
    0.64
    until
    0.64
    ãĥ¼ãĥ³
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.