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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.79
     مشين
    -0.75
    UserScript
    -0.62
     GenerationType
    -0.62
    :✨
    -0.62
    XmlAccessorType
    -0.60
    awtextra
    -0.59
     crdi
    -0.58
     Monfieur
    -0.58
     Jefus
    -0.57
    POSITIVE LOGITS
    ">)</
    0.55
    glom
    0.53
    '.
    0.52
    ofollow
    0.49
    becker
    0.49
    principalColumn
    0.47
    !).
    0.47
    עוד
    0.47
    ospital
    0.46
    ्यालय
    0.45
    Act Density 0.366%

    No Known Activations