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

    Neuronpedia

    INDEX
    Explanations

    the term "Standard" followed by a numerical value or in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific standard or regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ius
    -0.71
    pora
    -0.71
    fil
    -0.70
    ildo
    -0.69
    fle
    -0.66
    omez
    -0.65
    lov
    -0.64
     alienated
    -0.64
    rir
    -0.64
     cann
    -0.63
    POSITIVE LOGITS
     Standard
    3.79
    Standard
    2.66
     standard
    2.00
    standard
    1.85
     Standards
    1.83
     STAND
    1.43
     standards
    1.28
     Normal
    1.11
     Modern
    1.05
     Specifications
    1.05
    Act Density 0.005%

    No Known Activations