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

    Neuronpedia

    INDEX
    Explanations

    references to "pieces" and "parts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (!__
    -1.06
     nahilalakip
    -0.97
    GraphicsUnit
    -0.94
    LookAnd
    -0.92
    theless
    -0.92
    "]));
    -0.92
     Hald
    -0.90
     Мексичка
    -0.89
    ")));
    -0.89
     InputDecoration
    -0.88
    POSITIVE LOGITS
     pieces
    1.85
    Pieces
    1.81
     Pieces
    1.79
     piece
    1.72
     Piece
    1.62
    Piece
    1.58
     PIECE
    1.53
    pieces
    1.45
    piece
    1.40
    ECES
    1.28
    Act Density 0.068%

    No Known Activations