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

    Neuronpedia

    INDEX
    Explanations

    references to heroin

    oai_token-act-pair · gpt-3.5-turbo

    references to heroin and related substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.83
    ĨĴ
    -0.75
     Democr
    -0.74
    eor
    -0.73
    elong
    -0.70
    parts
    -0.69
    semble
    -0.68
     Ecc
    -0.68
    acular
    -0.68
    ech
    -0.67
    POSITIVE LOGITS
     heroin
    1.24
     overdoses
    1.08
     addict
    1.02
     addiction
    1.01
     overdose
    1.01
     opium
    0.90
     fentanyl
    0.90
     addicts
    0.90
     cocaine
    0.88
    avorite
    0.83
    Act Density 0.009%

    No Known Activations