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

    Neuronpedia

    INDEX
    Explanations

    numerical values such as times, dates, and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     satell
    -0.63
     plateau
    -0.61
     guiName
    -0.61
    merce
    -0.59
    plin
    -0.59
     autonom
    -0.57
    spread
    -0.56
     Nare
    -0.56
    orem
    -0.55
    iewicz
    -0.54
    POSITIVE LOGITS
    %)
    1.51
    %),
    1.34
    )=
    1.26
    )/
    1.24
    +)
    1.21
    )
    1.20
    ),"
    1.15
    )"
    1.14
    %).
    1.13
    %);
    1.13
    Act Density 0.072%

    No Known Activations