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

    Neuronpedia

    INDEX
    Explanations

    references to specific academic institutions and government departments

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blank
    -0.78
    oidal
    -0.76
    minus
    -0.73
    pause
    -0.69
    pedia
    -0.66
     sqor
    -0.64
     stride
    -0.63
    achev
    -0.62
    nation
    -0.62
    aldi
    -0.62
    POSITIVE LOGITS
     Health
    0.82
     Agriculture
    0.79
    Crime
    0.79
     Ethics
    0.78
     Photography
    0.78
     Excellence
    0.77
    veland
    0.77
     Commerce
    0.77
     Expo
    0.75
     Athletics
    0.74
    Act Density 0.089%

    No Known Activations