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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and expressions of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑı
    -0.17
    shiv
    -0.16
    tae
    -0.16
    ubl
    -0.14
    gia
    -0.14
    èĶ
    -0.14
    loyment
    -0.14
    .rawValue
    -0.13
    онд
    -0.13
     Sly
    -0.13
    POSITIVE LOGITS
    antar
    0.15
    nu
    0.15
    amura
    0.14
    urst
    0.14
    ant
    0.14
    jd
    0.14
    ifice
    0.14
    artz
    0.14
    cente
    0.14
    lore
    0.14
    Act Density 0.420%

    No Known Activations