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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arij
    -0.71
     aback
    -0.65
     Osw
    -0.63
    DragonMagazine
    -0.62
     sighting
    -0.62
    atta
    -0.61
     Finder
    -0.60
    earchers
    -0.59
    ocular
    -0.59
    uscript
    -0.58
    POSITIVE LOGITS
     theirs
    0.91
     shitty
    0.88
     senseless
    0.86
     mindless
    0.86
     democratically
    0.85
     immoral
    0.84
     THEIR
    0.83
     crappy
    0.83
     trillions
    0.83
     stupid
    0.82
    Act Density 1.144%

    No Known Activations