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

    Neuronpedia

    INDEX
    Explanations

    terms related to discrimination, authority, products, language, democracy, rights, scientific inquiry, integrity, maturity, benefit, leader, economy, profits, and communication

    oai_token-act-pair · gpt-3.5-turbo

    discussions about social justice issues and systemic inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.71
     Vaugh
    -0.65
    zens
    -0.59
    renheit
    -0.57
    everal
    -0.57
     Rober
    -0.56
    elve
    -0.56
     Alley
    -0.56
    ãĤ»
    -0.55
    arthed
    -0.54
    POSITIVE LOGITS
     doesnt
    0.99
    )?
    0.83
     depends
    0.80
    ↵Âł
    0.79
     implies
    0.75
     dont
    0.75
    .--
    0.74
     (%)
    0.74
    ¶
    0.72
     etc
    0.72
    Act Density 1.171%

    No Known Activations