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

    Neuronpedia

    INDEX
    Explanations

    quoted statements within text

    oai_token-act-pair · gpt-3.5-turbo

    direct quotations from individuals or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meddling
    -0.85
     riches
    -0.84
     egalitarian
    -0.84
     envy
    -0.83
     favor
    -0.83
     feminism
    -0.79
     socialist
    -0.79
     favour
    -0.79
     obsess
    -0.79
     feminists
    -0.78
    POSITIVE LOGITS
    Obviously
    1.48
    We
    1.43
    Typically
    1.41
    Certainly
    1.39
    Clearly
    1.36
    They
    1.35
    Our
    1.33
    Generally
    1.30
    Usually
    1.30
    There
    1.30
    Act Density 0.156%

    No Known Activations