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

    Neuronpedia

    INDEX
    Explanations

    references to dynamic concepts in statistical models or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     médicaux
    -0.79
     étrangère
    -0.74
     étoit
    -0.74
     polaire
    -0.72
     sauf
    -0.72
     noires
    -0.71
     littéraire
    -0.71
     vois
    -0.71
     gabinete
    -0.69
     Bact
    -0.68
    POSITIVE LOGITS
     dynamics
    1.48
     dynamic
    1.44
     dyna
    1.38
    ViewFeatures
    1.32
     dynamically
    1.31
     dynamis
    1.31
    dynamic
    1.30
    dynamics
    1.30
     Dynamic
    1.29
     dynamism
    1.28
    Act Density 0.077%

    No Known Activations