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

    Neuronpedia

    INDEX
    Explanations

    references to women and discussions around their roles and challenges in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to groups of people, particularly demographic categories and populations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     definition
    -0.39
    BeginInit
    -0.39
    concaten
    -0.39
     Vordergrund
    -0.39
     displays
    -0.37
     Einfluß
    -0.37
    displays
    -0.37
     rating
    -0.36
     coverage
    -0.36
    乐趣
    -0.36
    POSITIVE LOGITS
     educators
    0.85
     professionals
    0.72
     teachers
    0.68
     parents
    0.65
     individuals
    0.63
     moms
    0.62
     practitioners
    0.62
     policymakers
    0.61
     readers
    0.60
     aspiring
    0.60
    Act Density 0.610%

    No Known Activations