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

    Neuronpedia

    INDEX
    Explanations

    mentions of preservatives

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their political affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lia
    -0.70
    WN
    -0.70
     extingu
    -0.63
     Clause
    -0.63
     fries
    -0.62
     Camel
    -0.61
     Wonder
    -0.61
    itud
    -0.60
     MacBook
    -0.60
     Spit
    -0.59
    POSITIVE LOGITS
    eters
    2.79
    etts
    2.14
    ervatives
    2.08
    ervative
    1.95
     Emanuel
    1.26
     easing
    1.11
    artisan
    1.04
    eting
    0.99
    uchin
    0.98
    ets
    0.97
    Act Density 0.025%

    No Known Activations