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

    Neuronpedia

    INDEX
    Explanations

    mentions of communities or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    terms related to community and communal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.78
    OPLE
    -0.77
    olkien
    -0.74
    BALL
    -0.74
     pity
    -0.67
    OHN
    -0.66
     skirts
    -0.65
     Ole
    -0.64
    leaf
    -0.63
    DonaldTrump
    -0.62
    POSITIVE LOGITS
    icable
    1.54
    icator
    1.53
    icative
    1.46
    icators
    1.38
    icating
    1.28
    icate
    1.25
    icated
    1.15
    iqu
    1.12
    ique
    1.09
    ications
    1.07
    Act Density 0.029%

    No Known Activations