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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies, specifically mentioning conservatives

    oai_token-act-pair · gpt-3.5-turbo

    references to conservatives and their activities or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shard
    -0.77
    ship
    -0.76
    uner
    -0.75
    fleet
    -0.68
     Skype
    -0.66
    kit
    -0.65
    aqu
    -0.64
    aiden
    -0.64
    esc
    -0.63
     Halo
    -0.63
    POSITIVE LOGITS
     conservatives
    3.53
     liberals
    2.67
     progressives
    2.35
     conservatism
    2.35
     Conservatives
    2.28
     leftists
    2.21
     libertarians
    2.13
     Republicans
    1.97
     conservative
    1.95
     Democrats
    1.92
    Act Density 0.015%

    No Known Activations