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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and power struggles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    range
    -0.86
    tnc
    -0.75
    cific
    -0.75
    ificantly
    -0.71
    avia
    -0.71
    Ô
    -0.69
    alez
    -0.69
    anned
    -0.68
    gm
    -0.67
    rompt
    -0.66
    POSITIVE LOGITS
    ablishment
    0.99
     apparatus
    0.98
     elites
    0.98
     cabal
    0.91
     Establishment
    0.90
     elite
    0.90
     wisdom
    0.89
     establishment
    0.89
    eers
    0.87
     bureaucracy
    0.83
    Act Density 0.099%

    No Known Activations