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

    Neuronpedia

    INDEX
    Explanations

    special syntax elements and structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vœux
    -0.76
     navires
    -0.73
     négociations
    -0.72
     renseignements
    -0.71
     leçons
    -0.71
     lèvres
    -0.71
     épaules
    -0.69
     vérit
    -0.67
     gouvernements
    -0.67
     églises
    -0.65
    POSITIVE LOGITS
     ings
    0.66
     ARS
    0.66
     DMs
    0.65
    tols
    0.64
    ırs
    0.64
    rics
    0.62
    tams
    0.62
    kins
    0.61
    尔斯
    0.61
     limes
    0.60
    Act Density 0.976%

    No Known Activations