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

    Neuronpedia

    INDEX
    Explanations

    quotations within the text

    oai_token-act-pair · gpt-3.5-turbo

    quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favor
    -0.78
     honors
    -0.72
     muse
    -0.70
     grades
    -0.67
     Saiyan
    -0.67
     Mystic
    -0.66
     Savannah
    -0.66
     midterm
    -0.66
     Lamar
    -0.65
     plagiar
    -0.64
    POSITIVE LOGITS
    We
    1.17
    Firstly
    1.12
    Our
    1.11
    There
    1.05
    Such
    1.02
    It
    1.02
    BBC
    0.99
    People
    0.99
    Given
    0.98
    Today
    0.98
    Act Density 0.106%

    No Known Activations