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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies emphasizing freedom, rights, democracy, and equality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to human rights and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flames
    -0.78
    ulla
    -0.76
     Symptoms
    -0.75
    sbm
    -0.72
     Crusher
    -0.70
     Rats
    -0.68
    Mouse
    -0.67
    Sym
    -0.67
     Craw
    -0.67
     Printed
    -0.65
    POSITIVE LOGITS
     equality
    1.53
     democracy
    1.43
     egalitarian
    1.39
     neutrality
    1.35
     openness
    1.35
     fairness
    1.28
    equality
    1.28
     independence
    1.26
     decency
    1.26
     liberalism
    1.21
    Act Density 0.367%

    No Known Activations