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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and governance

    oai_token-act-pair · gpt-3.5-turbo

    references to societal and moral concepts related to the preservation and protection of cultural values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atten
    -0.80
    aily
    -0.69
    ãħĭãħĭ
    -0.67
    ali
    -0.66
    visual
    -0.65
    BIL
    -0.64
    recomm
    -0.64
    quit
    -0.63
    umo
    -0.62
    antically
    -0.62
    POSITIVE LOGITS
     vice
    0.85
     dignity
    0.84
     morals
    0.83
     consequently
    0.82
     thereby
    0.81
     freedoms
    0.81
     Zionism
    0.81
     academia
    0.81
     humankind
    0.80
     imperialism
    0.78
    Act Density 0.297%

    No Known Activations