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

    Neuronpedia

    INDEX
    Explanations

    technical terms or specific variables related to programming and biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.52
    migrationBuilder
    -0.48
     onBackPressed
    -0.47
     Italijanski
    -0.47
     RoutedEventArgs
    -0.47
     صوتيه
    -0.47
    HasBeenSet
    -0.45
     RouterModule
    -0.45
    исправ
    -0.44
     <>",
    -0.44
    POSITIVE LOGITS
    cla
    0.78
     cla
    0.75
     Cla
    0.71
     dive
    0.67
    Cla
    0.67
    dive
    0.60
     CLA
    0.60
     dives
    0.59
     Dive
    0.58
     divergence
    0.57
    Act Density 0.406%

    No Known Activations