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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions on various political and social topics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to personal and societal critiques of authority and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.51
     Sie
    -0.49
     Feder
    -0.49
    ILLE
    -0.49
     Lic
    -0.46
    Vel
    -0.46
     Hert
    -0.46
     Pwr
    -0.46
     Bod
    -0.46
     Vest
    -0.46
    POSITIVE LOGITS
     ideals
    0.68
     antics
    0.66
     injust
    0.65
     plight
    0.63
     evils
    0.62
     failures
    0.62
     indifference
    0.60
     negativity
    0.60
     menace
    0.60
    establishment
    0.60
    Act Density 1.370%

    No Known Activations