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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific references such as poll results, court opinions, media analysis, and official themes

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to polling and political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vain
    -0.78
     republican
    -0.73
     knit
    -0.61
    iannopoulos
    -0.60
     needles
    -0.59
    Downloadha
    -0.59
     crochet
    -0.58
     bake
    -0.58
     shave
    -0.58
     bulk
    -0.58
    POSITIVE LOGITS
     Works
    0.87
     Manager
    0.87
     Room
    0.85
     Week
    0.84
     Authority
    0.82
     Month
    0.82
     Corps
    0.80
     Blocks
    0.80
    Co
    0.80
     Accountability
    0.80
    Act Density 0.598%

    No Known Activations