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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures or events, particularly related to specific characters or periods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    boards
    -0.79
    д
    -0.73
    =-=-=-=-=-=-=-=-
    -0.68
    ãĥ£
    -0.68
    wick
    -0.65
    ãĤ§
    -0.64
    board
    -0.64
    notes
    -0.64
    rooms
    -0.63
    lisher
    -0.63
    POSITIVE LOGITS
    III
    1.05
    II
    1.03
    FY
    0.86
    HF
    0.82
    ATA
    0.69
    pec
    0.66
    ibur
    0.63
    HS
    0.62
    131
    0.62
    EC
    0.61
    Act Density 7.449%

    No Known Activations