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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product descriptions and releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to product releases and limited editions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kilometres
    -0.86
    vernment
    -0.81
     behavi
    -0.80
     negligence
    -0.73
    Population
    -0.73
     congest
    -0.73
    à©
    -0.73
     incompetence
    -0.72
    à¦
    -0.72
     hiber
    -0.71
    POSITIVE LOGITS
     Deluxe
    1.17
     Bundle
    1.13
     purch
    1.08
    uxe
    1.08
     priced
    1.07
     sleeve
    1.06
     Premium
    1.05
     Accessories
    1.04
     Printed
    1.03
     Collector
    1.03
    Act Density 0.640%

    No Known Activations