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

    Neuronpedia

    INDEX
    Explanations

    films directed and produced by specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to film production and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.62
     misplaced
    -0.62
     bureaucratic
    -0.60
     bureaucracy
    -0.59
    whatever
    -0.59
     bureaucrats
    -0.58
     bearings
    -0.58
    older
    -0.56
    MORE
    -0.56
    asive
    -0.56
    POSITIVE LOGITS
     by
    1.12
     BY
    0.98
    eaturing
    0.93
     jointly
    0.87
     By
    0.85
     exclusively
    0.82
    by
    0.76
    By
    0.75
     brilliantly
    0.72
     collabor
    0.71
    Act Density 0.105%

    No Known Activations