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

    Neuronpedia

    INDEX
    Explanations

    terms related to tolerance and its measurement in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    s
    -0.72
    Higgs
    -0.71
    $
    -0.63
    igshid
    -0.63
     Higgs
    -0.63
     eaux
    -0.63
     Gump
    -0.63
    ethene
    -0.62
    partiet
    -0.61
    arrol
    -0.61
    POSITIVE LOGITS
     Toler
    1.69
     tolerance
    1.64
     Tolerance
    1.60
    Toler
    1.60
     tolerant
    1.51
     tolerances
    1.48
    tolerant
    1.48
    tolerance
    1.46
     toler
    1.43
    toler
    1.42
    Act Density 0.007%

    No Known Activations