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

    Neuronpedia

    INDEX
    Explanations

    references to a specific person, Soros

    oai_token-act-pair · gpt-3.5-turbo

    mentions of George Soros and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olog
    -0.65
    bh
    -0.64
     introduced
    -0.64
    Jenn
    -0.64
    Temperature
    -0.62
     Adelaide
    -0.61
    ihar
    -0.61
    çĶ°
    -0.61
     curv
    -0.60
     Charl
    -0.60
    POSITIVE LOGITS
     Soros
    3.26
    oros
    2.28
     Maker
    1.48
    vernment
    1.33
    Maker
    1.10
    iannopoulos
    1.05
     FEC
    0.98
     olig
    0.98
     Yiannopoulos
    0.98
    antis
    0.97
    Act Density 0.016%

    No Known Activations