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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political roles and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating roles or positions of advisors or aides in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glances
    -0.68
     deductions
    -0.66
    rings
    -0.65
     sockets
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    need
    -0.61
     bundles
    -0.61
     pauses
    -0.61
    rences
    -0.60
    rio
    -0.59
    POSITIVE LOGITS
     testify
    0.76
     inform
    0.76
     ensure
    0.74
     whom
    0.74
     oversee
    0.73
     accompany
    0.73
     Misc
    0.73
    wered
    0.72
     protect
    0.72
     appease
    0.71
    Act Density 0.095%

    No Known Activations