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

    Neuronpedia

    INDEX
    Explanations

    references to the public in discussions of governance or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CreateModel
    -0.72
     rencont
    -0.70
     remercier
    -0.68
     sélectionnés
    -0.67
     שוליים
    -0.67
    ⓘ
    -0.66
     débar
    -0.65
     theologians
    -0.63
     réfugi
    -0.62
    DebuggerNonUser
    -0.62
    POSITIVE LOGITS
     public
    3.25
     Public
    2.91
    Public
    2.67
     PUBLIC
    2.49
     öffentlichen
    2.02
    PUBLIC
    2.01
     öffentliche
    2.00
     pública
    2.00
     público
    1.96
     pubblico
    1.91
    Act Density 0.066%

    No Known Activations