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

    Neuronpedia

    INDEX
    Explanations

    profession-related words, especially those related to scientific fields and research

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of professionals in various scientific and academic fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.71
     Beasts
    -0.69
    ãĥ¼ãĥ³
    -0.68
    inventoryQuantity
    -0.65
     Hague
    -0.64
     Deadly
    -0.64
     VIDEOS
    -0.63
     Onion
    -0.62
     Disapp
    -0.61
     Blacks
    -0.60
    POSITIVE LOGITS
     specializing
    1.33
     studying
    1.02
     researching
    0.93
     employed
    0.93
     stationed
    0.92
     who
    0.91
     visiting
    0.91
     with
    0.90
     practicing
    0.90
     at
    0.89
    Act Density 0.131%

    No Known Activations