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

    Neuronpedia

    INDEX
    Explanations

    references to manipulation and exploitation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.55
    URLException
    -0.55
     apporté
    -0.54
    forhold
    -0.53
     sexuelle
    -0.53
     riferimento
    -0.51
     partagé
    -0.50
     changé
    -0.49
     déterminé
    -0.49
    OGND
    -0.48
    POSITIVE LOGITS
    ']>
    0.60
    ViewImports
    0.59
    RegressionTest
    0.57
    :],
    0.56
    LookAnd
    0.56
    XmlAccessorType
    0.56
    挽回
    0.53
    ])):
    0.52
    __*/
    0.52
    ']],
    0.51
    Act Density 0.398%

    No Known Activations