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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal issues and welfare concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /write
    -0.21
    *width
    -0.19
     widely
    -0.18
     wastewater
    -0.18
    eur
    -0.17
    allet
    -0.17
     unwilling
    -0.17
     wavelengths
    -0.17
    weg
    -0.17
     wavelength
    -0.17
    POSITIVE LOGITS
    nesday
    0.23
    /month
    0.22
    owski
    0.22
    robe
    0.21
    abi
    0.19
    ows
    0.18
    tower
    0.18
    NES
    0.18
    ful
    0.17
    =w
    0.17
    Act Density 0.841%

    No Known Activations