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

    Neuronpedia

    INDEX
    Explanations

    references to tiles and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.43
    tedì
    -0.40
    GDPR
    -0.39
    HomeAsUpEnabled
    -0.38
     ActionBar
    -0.38
     Bach
    -0.38
     afec
    -0.38
     ErrIntOverflow
    -0.37
    editForm
    -0.36
    Biographie
    -0.36
    POSITIVE LOGITS
     tile
    0.78
     Tile
    0.77
    Tile
    0.75
     twin
    0.74
     athlete
    0.71
     Athletes
    0.67
     tiles
    0.66
     athletes
    0.66
    PerformLayout
    0.64
    Twin
    0.64
    Act Density 0.269%

    No Known Activations