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

    Neuronpedia

    INDEX
    Explanations

    tokens representing possessive forms or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ForRow
    -0.17
    _ios
    -0.15
    577
    -0.15
     Florian
    -0.15
     py
    -0.14
     Camden
    -0.14
     skon
    -0.14
    ROWS
    -0.14
    iscal
    -0.14
     backgrounds
    -0.14
    POSITIVE LOGITS
     piece
    0.20
    piece
    0.20
     Piece
    0.19
     pieces
    0.19
     Pieces
    0.18
    -piece
    0.18
    pieces
    0.18
    eltas
    0.18
    CRET
    0.17
     Bre
    0.17
    Act Density 0.029%

    No Known Activations