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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and methodologies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     perfect
    -0.49
    erste
    -0.48
    ced
    -0.47
     Green
    -0.47
    Types
    -0.47
    ara
    -0.44
     Perfect
    -0.43
     secret
    -0.42
    ärm
    -0.42
    ODA
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.27
    UnsafeEnabled
    1.02
     للاسماء
    0.96
    InjectAttribute
    0.93
     surla
    0.92
     propOrder
    0.90
     متعلقه
    0.88
    ViewFeatures
    0.88
    RTLD
    0.88
     saites
    0.87
    Act Density 0.025%

    No Known Activations