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

    Neuronpedia

    INDEX
    Explanations

    words related to enjoyment, satisfaction, or positive experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pleasure" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enz
    -0.70
    ept
    -0.68
    enhagen
    -0.66
    soType
    -0.66
    atown
    -0.65
    ename
    -0.63
    pat
    -0.63
    ynski
    -0.62
     Apocalypse
    -0.61
     Greenpeace
    -0.60
    POSITIVE LOGITS
     pleasure
    1.12
    joy
    0.94
    ously
    0.88
     pleas
    0.86
     enjoyment
    0.86
    obbies
    0.86
    fully
    0.85
     pleasures
    0.85
    sticks
    0.84
    ishment
    0.83
    Act Density 0.015%

    No Known Activations