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

    Neuronpedia

    INDEX
    Explanations

    references to the drug heroin

    oai_token-act-pair · gpt-3.5-turbo

    references to the drug heroin and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tten
    -0.82
    oÄŁ
    -0.78
    rons
    -0.77
     Democr
    -0.77
    parts
    -0.76
    ghai
    -0.72
    semble
    -0.71
    ĨĴ
    -0.70
    eor
    -0.69
     MacArthur
    -0.68
    POSITIVE LOGITS
     addiction
    1.06
     overdoses
    1.02
     addict
    1.01
     overdose
    1.00
     heroin
    0.99
     addicts
    0.96
     needles
    0.84
     withdrawal
    0.81
     relapse
    0.81
     addicted
    0.79
    Act Density 0.010%

    No Known Activations