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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive emotions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ux
    -0.15
    egasus
    -0.14
     prop
    -0.14
    .Transactional
    -0.14
    ute
    -0.14
    ENCH
    -0.13
    Ñĩи
    -0.13
    hi
    -0.13
     Chill
    -0.13
    undai
    -0.13
    POSITIVE LOGITS
    velt
    0.19
    oola
    0.18
    shine
    0.15
    vÄĽd
    0.15
    ospace
    0.14
    ÏĦαÏĤ
    0.14
    amet
    0.14
    onec
    0.14
    ená
    0.14
    rece
    0.14
    Act Density 0.032%

    No Known Activations