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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "piece" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (!__
    -1.07
     nahilalakip
    -0.95
    esercito
    -0.94
     ExecuteAsync
    -0.92
     noDo
    -0.88
     HasFactory
    -0.88
     Hald
    -0.88
     ")");
    -0.87
    "]));
    -0.86
    theless
    -0.86
    POSITIVE LOGITS
     pieces
    2.03
     Pieces
    1.93
    Pieces
    1.92
     piece
    1.92
     Piece
    1.81
    Piece
    1.74
     PIECE
    1.71
    pieces
    1.62
    piece
    1.58
    PIECE
    1.35
    Act Density 0.049%

    No Known Activations