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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.17
    antz
    -0.16
    RELEASE
    -0.15
    ongan
    -0.14
    rvé
    -0.14
    ugg
    -0.14
    emo
    -0.14
    -expanded
    -0.14
    78
    -0.14
    urdu
    -0.14
    POSITIVE LOGITS
     Maxim
    0.14
    udden
    0.14
    ijn
    0.14
    fik
    0.14
    icorn
    0.14
    Hierarchy
    0.13
     Penal
    0.13
    imas
    0.13
    forced
    0.13
    udo
    0.13
    Act Density 0.067%

    No Known Activations