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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political movements and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to political initiatives and campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urities
    -0.69
    uitous
    -0.68
    umerable
    -0.67
    theless
    -0.67
    imentary
    -0.66
    >[
    -0.65
     moreover
    -0.64
    etheless
    -0.64
     sorcerer
    -0.64
     palp
    -0.62
    POSITIVE LOGITS
    !,
    1.14
     Stupid
    0.92
     Forever
    0.91
     Yourself
    0.89
     Initiative
    0.88
     Everywhere
    0.88
     Hate
    0.85
     Tomorrow
    0.85
     Faith
    0.84
     Choice
    0.84
    Act Density 0.789%

    No Known Activations