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

    Neuronpedia

    INDEX
    Explanations

    words related to positive emotions, especially joy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "joy" and related expressions of happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.67
    iban
    -0.62
     deductible
    -0.60
     conflic
    -0.60
     underest
    -0.60
     stockp
    -0.59
     fragmented
    -0.59
     comma
    -0.58
     Rhod
    -0.58
     Breach
    -0.58
    POSITIVE LOGITS
    sticks
    1.47
    fully
    1.31
    ously
    1.28
    ous
    1.16
    joy
    1.14
    iously
    1.05
    ride
    1.01
    stick
    0.98
    son
    0.96
    ilee
    0.93
    Act Density 0.016%

    No Known Activations