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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity and worldwide representation

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity or universality across various groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.81
    pd
    -0.66
    kamp
    -0.66
     Caption
    -0.65
    undo
    -0.61
    uction
    -0.60
    etter
    -0.60
    venge
    -0.60
     Maiden
    -0.59
     largeDownload
    -0.58
    POSITIVE LOGITS
     sorts
    1.61
     kinds
    1.58
     types
    1.22
     facets
    1.20
     shapes
    1.15
     aspects
    1.10
    iances
    1.08
     ages
    1.07
     genres
    1.07
     phases
    1.07
    Act Density 0.068%

    No Known Activations