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

    Neuronpedia

    INDEX
    Explanations

    references to demo content or examples in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dem
    -0.71
    dem
    -0.69
    ="'.$
    -0.65
    entity
    -0.64
    arte
    -0.64
     bross
    -0.62
     familiari
    -0.60
    Cubit
    -0.59
    als
    -0.59
     Dem
    -0.59
    POSITIVE LOGITS
     demo
    1.02
     Phry
    0.94
     demos
    0.90
     ujednoznacz
    0.88
    demo
    0.84
    screening
    0.84
     Winona
    0.81
    tanleria
    0.80
     Demo
    0.79
     démo
    0.78
    Act Density 0.044%

    No Known Activations