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

    Neuronpedia

    INDEX
    Explanations

    mentions of governmental actions or involvements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various governments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranging
    -0.72
     Rider
    -0.70
    ãĥ¼ãĥĨ
    -0.68
    Dialog
    -0.67
     Modes
    -0.66
    uesday
    -0.65
    actionDate
    -0.63
    lihood
    -0.63
     Kind
    -0.63
    iable
    -0.63
    POSITIVE LOGITS
     officials
    0.87
     bureaucracy
    0.82
    orate
    0.79
     embassy
    0.78
     intervened
    0.78
    eers
    0.77
     delegation
    0.76
     sanctioned
    0.76
     inspector
    0.75
     authorities
    0.75
    Act Density 0.059%

    No Known Activations