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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bered
    -0.73
     vag
    -0.69
     pee
    -0.67
     mapping
    -0.67
     outsourcing
    -0.64
     listening
    -0.64
     opting
    -0.63
     brunch
    -0.63
     constructive
    -0.62
     broadcasting
    -0.62
    POSITIVE LOGITS
    We
    1.06
    I
    0.97
    They
    0.95
    Interest
    0.94
    Too
    0.93
    People
    0.92
    It
    0.91
    There
    0.90
    Non
    0.89
    BuyableInstoreAndOnline
    0.89
    Act Density 0.094%

    No Known Activations