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

    Neuronpedia

    INDEX
    Explanations

    words related to political or social ideologies that carry a certain weight or influence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspended
    -0.71
     Pwr
    -0.65
    alls
    -0.64
     Bucks
    -0.64
     round
    -0.63
    ires
    -0.63
     Browns
    -0.62
     Steps
    -0.62
     Dee
    -0.61
     snapped
    -0.61
    POSITIVE LOGITS
     ideology
    3.37
     ideologies
    2.44
     ideological
    2.22
     Ide
    2.04
     ideologically
    1.82
     dogma
    1.75
     ethos
    1.61
     worldview
    1.59
     ide
    1.59
     orthodoxy
    1.54
    Act Density 0.023%

    No Known Activations