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

    Neuronpedia

    INDEX
    Explanations

    terms related to terms of service and user agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to terms of use and violations in agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    albeit
    -0.74
    few
    -0.72
    ciation
    -0.71
     plenty
    -0.70
    almost
    -0.68
    pretty
    -0.68
    mostly
    -0.67
    ciating
    -0.67
    leneck
    -0.66
     mostly
    -0.65
    POSITIVE LOGITS
     Products
    0.92
     products
    0.92
     Content
    0.87
     ANY
    0.86
     trademarks
    0.84
     or
    0.83
     advertisements
    0.83
     nor
    0.83
     SERVICES
    0.83
     materials
    0.82
    Act Density 0.375%

    No Known Activations