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

    Neuronpedia

    INDEX
    Explanations

    concepts related to addiction and its effects on the brain's pleasure and reward systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻes
    -0.15
    è³¢
    -0.14
    loat
    -0.14
    onest
    -0.13
     sinc
    -0.12
    dech
    -0.12
    ARB
    -0.12
    bil
    -0.12
    áo
    -0.12
    اظ
    -0.12
    POSITIVE LOGITS
     reward
    0.38
     pleasure
    0.34
     dopamine
    0.33
     Reward
    0.33
     rewarding
    0.32
    Reward
    0.31
     craving
    0.31
    reward
    0.30
     rewards
    0.30
     ple
    0.30
    Act Density 0.080%

    No Known Activations