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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their roles or professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..
    -0.96
    aucas
    -0.88
     !!
    -0.88
    ����
    -0.81
     doesnt
    -0.81
    `
    -0.80
     %
    -0.80
     didnt
    -0.79
    ""
    -0.78
    ,,,,
    -0.77
    POSITIVE LOGITS
     Slate
    1.02
    —"
    0.98
     VICE
    0.92
    Enlarge
    0.89
     Weird
    0.87
     Chromebook
    0.86
     nifty
    0.86
     weird
    0.85
     goofy
    0.85
     dudes
    0.84
    Act Density 1.820%

    No Known Activations