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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern and skepticism regarding governmental and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jou
    -0.68
    BuyableInstoreAndOnline
    -0.66
     Albania
    -0.64
     Dres
    -0.62
    essen
    -0.62
    eger
    -0.61
     Hermes
    -0.60
     Feather
    -0.60
    erala
    -0.59
     Dup
    -0.59
    POSITIVE LOGITS
    ģĸ
    0.75
    avior
    0.70
    SPONSORED
    0.70
    might
    0.69
    ļé
    0.68
    orrow
    0.66
     possessed
    0.64
    oke
    0.64
    overed
    0.63
    aviour
    0.63
    Act Density 0.436%

    No Known Activations