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

    Neuronpedia

    INDEX
    Explanations

    references to parts or fragments

    oai_token-act-pair · gpt-3.5-turbo

    references to multiple segments or components of various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.74
    export
    -0.72
    ync
    -0.70
    announced
    -0.69
    close
    -0.68
    mit
    -0.66
    afe
    -0.66
    ior
    -0.61
     postponed
    -0.59
     Marriott
    -0.59
    POSITIVE LOGITS
     pieces
    3.87
     Pieces
    2.86
    pieces
    2.44
     piece
    2.27
     bits
    1.90
     fragments
    1.84
     chunks
    1.82
     shards
    1.61
     Piece
    1.58
    piece
    1.46
    Act Density 0.010%

    No Known Activations