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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of assembly or connection, particularly using metaphors related to puzzles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŃĴ
    -0.17
    unload
    -0.14
     nackte
    -0.14
    é¼ĵ
    -0.14
     split
    -0.14
    fork
    -0.13
    _BT
    -0.13
    iez
    -0.13
    _RAW
    -0.13
    èĭĹ
    -0.13
    POSITIVE LOGITS
     puzzle
    0.59
     Puzzle
    0.50
     puzzles
    0.48
    igsaw
    0.35
     pieces
    0.33
     puzz
    0.32
     fit
    0.28
    uzzle
    0.28
     Pieces
    0.27
     piece
    0.27
    Act Density 0.023%

    No Known Activations