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

    Neuronpedia

    INDEX
    Explanations

    references to types of tiles and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crop
    -0.16
    uckles
    -0.15
     Chandler
    -0.15
     Cloth
    -0.15
     rac
    -0.15
     cloth
    -0.15
    á»
    -0.14
     fabrics
    -0.14
     fabric
    -0.14
     Hemp
    -0.14
    POSITIVE LOGITS
     tiles
    0.51
     tile
    0.50
     Tile
    0.44
     Tiles
    0.44
    tile
    0.42
    Tiles
    0.40
    .tile
    0.40
    Tile
    0.39
    tiles
    0.39
    (tile
    0.39
    Act Density 0.036%

    No Known Activations