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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social or political identity and comparison

    oai_token-act-pair · gpt-3.5-turbo

    references to societal structures and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.64
     Strat
    -0.63
    actionDate
    -0.63
    BG
    -0.62
    IVERS
    -0.60
    Acknowled
    -0.59
    yrics
    -0.59
    nance
    -0.58
     surpr
    -0.58
    assetsadobe
    -0.57
    POSITIVE LOGITS
     apiece
    0.98
    undred
    0.76
    ilion
    0.68
    fecture
    0.67
     per
    0.67
    inkle
    0.64
     alone
    0.64
    icka
    0.64
    anooga
    0.64
     individually
    0.64
    Act Density 0.156%

    No Known Activations