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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public speaking or statements made in public settings

    oai_token-act-pair · gpt-3.5-turbo

    components related to press conferences and public statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,'
    -0.70
     ',
    -0.70
    ',
    -0.67
    ',"
    -0.62
    !'
    -0.62
     fuckin
    -0.61
    ?'
    -0.61
     Prelude
    -0.61
    ,'"
    -0.59
     whilst
    -0.58
    POSITIVE LOGITS
     paraph
    0.68
     behalf
    0.66
    unci
    0.65
    etz
    0.64
    é¾
    0.64
    Recomm
    0.62
    pport
    0.62
     understatement
    0.61
    >]
    0.60
     Fried
    0.60
    Act Density 0.786%

    No Known Activations