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

    Neuronpedia

    INDEX
    Explanations

    nouns related to political manipulation or extremism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.74
    flix
    -0.73
    sheet
    -0.72
    dry
    -0.67
    EVA
    -0.64
    wards
    -0.63
     Kaw
    -0.63
    scope
    -0.63
     WWF
    -0.62
     LAST
    -0.62
    POSITIVE LOGITS
    agog
    1.49
    agogue
    1.27
    ues
    1.05
    acles
    0.97
    urations
    0.96
    allery
    0.95
    ically
    0.91
    atory
    0.91
    ococ
    0.89
    owitz
    0.89
    Act Density 0.022%

    No Known Activations