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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics related to political opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     organising
    -0.73
     Boat
    -0.68
    kid
    -0.65
    boy
    -0.63
    flash
    -0.63
    Hack
    -0.63
    DragonMagazine
    -0.62
     Maker
    -0.62
     traveller
    -0.62
     Hodg
    -0.61
    POSITIVE LOGITS
     percent
    1.63
    %
    1.40
    %)
    1.38
    %;
    1.38
    %).
    1.36
    %,
    1.33
    %.
    1.31
    %"
    1.27
    %:
    1.27
    %),
    1.25
    Act Density 0.074%

    No Known Activations