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

    Neuronpedia

    INDEX
    Explanations

    references to elite status or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to elite groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drawn
    -0.78
    externalActionCode
    -0.76
     Caption
    -0.75
    alone
    -0.71
    yah
    -0.71
    gm
    -0.68
    ventory
    -0.67
    given
    -0.67
    ========
    -0.67
    =-=-
    -0.66
    POSITIVE LOGITS
     elite
    1.09
     mosqu
    1.02
     acad
    0.90
     academy
    0.89
     elites
    0.81
     veter
    0.80
     athlete
    0.76
     athletes
    0.76
     prep
    0.75
     equival
    0.74
    Act Density 0.016%

    No Known Activations