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

    Neuronpedia

    INDEX
    Explanations

    references to floating-point data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.87
     sī
    -0.66
     jaunes
    -0.61
     connaissent
    -0.61
     وتسجيلات
    -0.59
     sauvages
    -0.59
    +#+
    -0.58
     devront
    -0.57
     devra
    -0.57
     blessés
    -0.57
    POSITIVE LOGITS
     float
    4.60
     Float
    3.87
     floats
    3.86
    float
    3.58
     FLOAT
    3.47
    Float
    3.34
     floating
    3.33
     floated
    3.21
     Floating
    2.89
    FLOAT
    2.66
    Act Density 0.066%

    No Known Activations