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

    Neuronpedia

    INDEX
    Explanations

    references to written or digital messages

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    engeance
    -0.73
    itect
    -0.72
    abama
    -0.71
    ibl
    -0.71
     Sketch
    -0.70
    aughs
    -0.67
    itates
    -0.66
    pmwiki
    -0.66
    itals
    -0.64
    ilts
    -0.64
    POSITIVE LOGITS
     boards
    1.04
    board
    1.04
     messages
    0.98
    boards
    0.97
    boxes
    0.96
     sent
    0.95
     inbox
    0.92
     board
    0.89
     Boards
    0.88
    box
    0.87
    Act Density 0.037%

    No Known Activations