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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    珹
    -0.07
    ɧ
    -0.07
    _missing
    -0.07
    בדק
    -0.07
    .stderr
    -0.06
     credible
    -0.06
     aDecoder
    -0.06
    제도
    -0.06
     uda
    -0.06
    mental
    -0.06
    POSITIVE LOGITS
    $file
    0.07
    fontWeight
    0.07
    .optimize
    0.07
    ibold
    0.07
     basin
    0.07
    _AUT
    0.07
    いくら
    0.07
     remarked
    0.07
    "},
↵
    0.07
    andReturn
    0.06
    Act Density 0.004%

    No Known Activations