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

    Neuronpedia

    INDEX
    Explanations

    concepts related to assembling and connecting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vlan
    -0.15
    Unload
    -0.15
    Pitch
    -0.14
    pitch
    -0.14
    phas
    -0.14
    ioxide
    -0.14
    unload
    -0.14
     Depths
    -0.13
    Pair
    -0.13
     yük
    -0.13
    POSITIVE LOGITS
     pieces
    0.71
     Pieces
    0.60
     piece
    0.56
    pieces
    0.52
     puzzle
    0.50
    Pieces
    0.50
     Piece
    0.47
    -piece
    0.46
     Puzzle
    0.46
    _pieces
    0.45
    Act Density 0.162%

    No Known Activations