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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    specific names and titles associated with people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colossus
    -0.63
     idiots
    -0.63
     partying
    -0.62
     subsistence
    -0.62
     ultras
    -0.60
     bullshit
    -0.59
     audiences
    -0.59
     underwater
    -0.58
     paradise
    -0.58
     Oprah
    -0.58
    POSITIVE LOGITS
    ansky
    1.13
    atz
    1.08
    owski
    1.02
    elman
    1.01
    enberg
    1.01
    acci
    1.01
    gaard
    1.01
    chini
    1.01
    ovsky
    1.00
    inski
    1.00
    Act Density 0.655%

    No Known Activations