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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating medical caution or the need for monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.17
    ippet
    -0.16
    rupa
    -0.15
    asics
    -0.15
    zia
    -0.15
    nech
    -0.14
    efeller
    -0.14
    /INFO
    -0.14
     GUIContent
    -0.14
    å¨
    -0.14
    POSITIVE LOGITS
     others
    0.17
    ogue
    0.16
     even
    0.15
     Nem
    0.15
     Andrews
    0.15
     Others
    0.14
     depending
    0.14
    çĶļèĩ³
    0.14
    ertas
    0.14
    atches
    0.14
    Act Density 0.186%

    No Known Activations