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

    Neuronpedia

    INDEX
    Explanations

    terms relating to dynamic systems and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
     étrangère
    -0.71
     Dover
    -0.69
     atteinte
    -0.66
     Sochi
    -0.65
    Dover
    -0.65
     italiane
    -0.64
     noires
    -0.64
    CloseOperation
    -0.64
     Hongrie
    -0.63
    POSITIVE LOGITS
     dynamics
    1.30
    dynamics
    1.20
     dyna
    1.17
     dynamic
    1.13
     dynamically
    1.12
     dynamism
    1.12
     Dynamics
    1.11
    ViewFeatures
    1.11
     dynamis
    1.10
     Dyna
    1.09
    Act Density 0.061%

    No Known Activations