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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and the assessment of their policies

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     english
    -0.81
     civilisation
    -0.71
     youtube
    -0.70
     ðŁĻĤ
    -0.68
     âĸĪ
    -0.66
     negro
    -0.65
     Youtube
    -0.65
    !!
    -0.65
     whilst
    -0.65
     fucking
    -0.64
    POSITIVE LOGITS
     worries
    0.94
     complicate
    0.90
     undersc
    0.89
     risks
    0.88
     wary
    0.86
     POLITICO
    0.83
     worrisome
    0.83
     jeopard
    0.82
     potentially
    0.82
     likely
    0.82
    Act Density 1.204%

    No Known Activations