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

    Neuronpedia

    INDEX
    Explanations

    words related to political ideologies and governmental systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political ideologies and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    each
    -0.86
    hots
    -0.83
    .<
    -0.80
    ;;
    -0.79
    ľ
    -0.71
     ..........
    -0.71
    registered
    -0.69
    possibly
    -0.69
    thia
    -0.69
    hops
    -0.68
    POSITIVE LOGITS
     ethos
    1.25
     tendency
    1.22
     mindset
    1.21
     rationale
    1.20
     notion
    1.20
     assumption
    1.19
     aristocracy
    1.17
     psyche
    1.16
     paradigm
    1.16
     implications
    1.15
    Act Density 0.304%

    No Known Activations