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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to assembling or reconciling fragmented elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pitch
    -0.16
    unload
    -0.16
    vlan
    -0.15
    jedn
    -0.15
    Unload
    -0.15
    Pitch
    -0.15
    vang
    -0.15
     Rencontre
    -0.14
    anean
    -0.14
    pairs
    -0.14
    POSITIVE LOGITS
     pieces
    0.72
     Pieces
    0.61
     piece
    0.58
     puzzle
    0.56
    pieces
    0.54
    Pieces
    0.51
    -piece
    0.50
     Piece
    0.49
     Puzzle
    0.48
    _pieces
    0.45
    Act Density 0.169%

    No Known Activations