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

    Neuronpedia

    INDEX
    Explanations

    references to "pieces of" something, indicating a focus on fragments or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.91
     ISNI
    -0.86
    GraphicsUnit
    -0.85
    (!__
    -0.83
    tagHelperRunner
    -0.81
     nahilalakip
    -0.80
     theſe
    -0.77
     loisirs
    -0.77
    Còn
    -0.77
    InitVars
    -0.76
    POSITIVE LOGITS
     pieces
    1.37
     Pieces
    1.24
    Pieces
    1.22
     piece
    1.13
     Piece
    1.07
    pieces
    1.03
     PIECE
    0.97
    Piece
    0.95
    piece
    0.86
    meal
    0.85
    Act Density 0.090%

    No Known Activations