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

    Neuronpedia

    INDEX
    Explanations

    actions or orders issued by an authority

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    edin
    -1.06
    sonian
    -0.83
    é¾
    -0.79
    nick
    -0.77
    bell
    -0.77
    beat
    -0.76
    acci
    -0.76
    aan
    -0.74
    hew
    -0.73
    jet
    -0.71
    POSITIVE LOGITS
    bidden
    1.24
    gery
    1.11
    geries
    1.10
     purposes
    1.03
     starters
    0.98
    aging
    0.89
     those
    0.88
     sake
    0.87
     instance
    0.87
     determining
    0.86
    Act Density 0.287%

    No Known Activations