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

    Neuronpedia

    INDEX
    Explanations

    words related to happiness

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "happy" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.69
     override
    -0.64
     Nile
    -0.63
     Kraft
    -0.61
    UA
    -0.60
     Arts
    -0.60
    İĭ
    -0.58
    coni
    -0.57
     Schiff
    -0.57
     Lange
    -0.56
    POSITIVE LOGITS
    ened
    1.54
    ening
    1.49
    ily
    1.34
    iest
    1.23
    iness
    1.21
    ens
    1.09
    eners
    1.08
    ier
    1.02
    erc
    1.01
    INESS
    0.96
    Act Density 0.063%

    No Known Activations