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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific groups of people or positions, such as "representative," "program managers," "nudists," "middle-class Americans," and "writer advocates."

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fla
    -0.82
    Tenn
    -0.75
    Jess
    -0.73
     Tropical
    -0.73
    Ore
    -0.72
    Nev
    -0.70
    Planet
    -0.69
    onet
    -0.66
    Ga
    -0.65
    Closure
    -0.65
    POSITIVE LOGITS
     are
    1.41
     aren
    1.27
     behave
    1.23
     tend
    1.22
     themselves
    1.20
     were
    1.19
     cannot
    1.16
     behaved
    1.12
     excel
    1.11
     prefer
    1.11
    Act Density 0.436%

    No Known Activations