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

    Neuronpedia

    INDEX
    Explanations

    references to political ideology associated with libertarianism

    oai_token-act-pair · gpt-3.5-turbo

    references to liberty and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.84
    isSpecialOrderable
    -0.84
     Origin
    -0.76
    BALL
    -0.68
     Bridges
    -0.65
    smanship
    -0.64
    ||||
    -0.64
    avorite
    -0.63
     Styles
    -0.63
     Drinking
    -0.62
    POSITIVE LOGITS
    ation
    1.10
    ated
    1.09
    ating
    1.00
    ations
    0.85
    ration
    0.83
    ization
    0.80
    tarian
    0.80
    imar
    0.78
    liber
    0.78
    ateurs
    0.78
    Act Density 0.025%

    No Known Activations