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

    Neuronpedia

    INDEX
    Explanations

    key phrases and terms related to accountability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.17
    illus
    -0.16
    arker
    -0.15
    æĺĩ
    -0.15
    loi
    -0.15
    uzzi
    -0.14
     Bands
    -0.14
    xious
    -0.14
    uman
    -0.14
     Patterson
    -0.14
    POSITIVE LOGITS
    /Application
    0.15
    gli
    0.14
     Tracy
    0.14
    _probe
    0.14
    aled
    0.14
    .APPLICATION
    0.14
    .son
    0.14
    émon
    0.13
     elig
    0.13
     doorstep
    0.13
    Act Density 0.001%

    No Known Activations