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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political, societal, and constitutional commentary, with a focus on issues and controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to "our" as a possessive indicator relating to collective ownership or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    puff
    -0.81
    FU
    -0.74
    netflix
    -0.73
    bender
    -0.73
    Downloadha
    -0.69
    wic
    -0.69
    tar
    -0.66
    icates
    -0.65
     externalToEVAOnly
    -0.64
    Å¡
    -0.64
    POSITIVE LOGITS
    selves
    1.36
     own
    1.28
     nation
    1.00
     collective
    0.97
     constitution
    0.94
     adversaries
    0.91
     beloved
    0.90
     ancestors
    0.89
     predicament
    0.89
     adversary
    0.88
    Act Density 0.115%

    No Known Activations