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

    Neuronpedia

    INDEX
    Explanations

    references to internships and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.17
    kou
    -0.15
    erase
    -0.14
    .gdx
    -0.14
    RootElement
    -0.14
    iola
    -0.14
    илÑı
    -0.14
    elan
    -0.13
    eroon
    -0.13
    back
    -0.13
    POSITIVE LOGITS
    ships
    0.20
    ship
    0.15
    snd
    0.15
    adge
    0.14
     Paper
    0.14
    اشت
    0.14
    oday
    0.14
    adas
    0.13
    hone
    0.13
    uai
    0.13
    Act Density 0.011%

    No Known Activations