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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity and equality for all

    oai_token-act-pair · gpt-3.5-turbo

    references to universal inclusion and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.73
    flation
    -0.68
    edin
    -0.64
    argon
    -0.62
    aminer
    -0.60
    hill
    -0.59
    illy
    -0.58
    CLAIM
    -0.58
    assembly
    -0.58
    crow
    -0.57
    POSITIVE LOGITS
    ocating
    1.12
     kinds
    1.09
     sorts
    1.04
     stakeholders
    1.01
     facets
    0.98
    igators
    0.95
    iances
    0.95
     genders
    0.93
     Mankind
    0.91
     mankind
    0.88
    Act Density 0.094%

    No Known Activations