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

    Neuronpedia

    INDEX
    Explanations

    references to assembling or combining parts into a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bote
    -0.18
    Pitch
    -0.14
    .synthetic
    -0.14
    vlan
    -0.14
    BT
    -0.14
    ãĥ³ãĤ¹
    -0.13
    unload
    -0.13
    raž
    -0.13
     Strap
    -0.13
     Silk
    -0.13
    POSITIVE LOGITS
     pieces
    0.57
     puzzle
    0.55
     piece
    0.52
     Puzzle
    0.49
     Pieces
    0.47
     Piece
    0.44
    -piece
    0.43
    pieces
    0.42
     puzzles
    0.42
    Pieces
    0.40
    Act Density 0.118%

    No Known Activations